SlideShare a Scribd company logo
Deep Learning for Cyber Security
.
Steven Hutt steven.c.hutt@gmail.com
28 February, 2017
Cyber Security
www.dropbox.gov
Why now?
• DNC, Sony, Yahoo, ...
• attack vectors constantly changing
• static detection approaches failing
• large amounts of data
• Deep Learning for anomaly detection
• corporate / government motivated
1
The Challenge
Can we apply Deep Learning to Cyber Security and better identify malicious
network traffic?
Reasons to be Optimistic:
• Plenty of data
• Good progress in general area of unsupervised feature selection
• Good progress in general area of anomaly detection
• Very topical subject - so that's good!
Reasons to be Skeptical:
• Practical usage requires very low false positive rate
• Essentially no labelled data
• Data is a hybrid of categorical (mostly) and numeric (some)
• Very topical subject - so why are there so few commercial successes?
Reasons to try:
• potentially huge market
• it's fun
2
Network Flow: the unit of data
A network flow is a record of the information exchanged via packets
between a source and a destination machine during the course of the
network protocol session.
ipv4Source 192.104.50.16 hasAttach True
ipv4Dest 147.135.57.43 sizeAttach 87
portSource 80 mimeType avi
portDest 1639 numAttach 1
latitude -5.31858 cookie 'name=kpl; expires=...'
longitude 81.52040 subject 'Re: meeting'
duration 13.87 searchString 'free beer'
timeStamp 1486034657716 urlString 'https://test-cloud-p...'
Network flow values are a hybrid of categorical, numerical and text data.
Deep Learning for numerical and text data has been extensively developed.
Here we focus on Deep Learning for categorical data.
3
Unsupervised Anomaly Detection
We attempt to fit a probability distribution to the data {xk}N
k=1. Many
approaches are possible. We focus here on generative models:
..z.
x
. pθ(z).
pθ(x)
. prior.
likelihood
.
marginal
.
posterior
.
pθ(x | z)
.
pθ(z | x)
Maximize log-likelihood of data:
pθ(x) =
∑
z
pθ(x | z)pθ(z)
ˆθ = arg min
θ
N∑
k=1
log
∑
z
pθ(xk | z)pθ(z)
Possible uses of generative model:
• A data point x is labelled anomalous if pˆθ(x) is below some threshold.
• The posterior pˆθ(z | x) determines unsupervised feature extraction z of
the data x. Features z can then be used in subsequent anomaly
detection model.
4
Categorical Distributions
Deep Learning for categorical data has been less studied than for numerical
or text data, so we focus on modelling multivariate categorical distributions.
Let x = {x1, . . . , xp} be categorical variables with xj ∈ {1, . . . , dj}, j = 1, . . . p.
Let π be a probability distribution on x:
πc1...cp = P(x1 = c1, . . . , xp = cp),
Then there exists:
1. an integer k > 0
2. a mixing variable z ∈ {1, . . . , k} with distribution ν = (ν1, . . . , νk)
3. a set of independent distributions ψ
(j)
hcj
= P(xj = cj | z = h)
such that
πc1...cp = P(x1 = c1, . . . , xp = cp) =
k∑
h=1
νk
p
∏
j=1
ψ
(j)
hcj
.
In other words, every multivariate categorical distribution is a mixture of
multivariate categorical distributions with independent marginals.
5
Problems
While the mixture representation result is encouraging there are several
challenges:
1. Direct likelihood maximization is computationally very expensive
2. Stochastic Gradient Descent is not possible as variables are discrete
3. The size k of the mixing variable is geometric in the dimension p
In order to address these challenges, we will utilize the following:
1. variational inference for approximate likelihood maximization
2. Gumbel softmax to relax categorical variables to continuous variables
3. Dirichlet processes to incorporate k as part of the inference
6
Variational Autoencoders in a Nutshell
Recall we wish to compute
ˆθ = arg min
θ
N∑
k=1
log
∑
z
pθ(xk | z)pθ(z)
so we need to efficiently compute
∑
z pθ(xk | z)pθ(z).
We can (badly) approximate by sampling:
∑
z
pθ(xk | z)pθ(z) ≃
M∑
i=1
pθ(xk | zi), where zi ∼ pθ(z)
But most of the time pθ(xk | zi) ≃ 0 so sample from zi ∼ pθ(z | xk) instead.
But pθ(z | xk) is the wrong distribution and is unknown...
... so we learn an approximation qϕ(z | xk) to the unknown pθ(z | xk)
... and account for the wrong distribution via a likelihood upper bound:
Lθ,ϕ(xk) = −DKL(qϕ(z | xk)||pθ(z))
regularization term
+ Eqϕ (log pθ(xk | z))
reconstruction term
Think of qϕ(z | x) : x → z as an encoder and pθ(x | z) : z → x as a decoder.
7
The Reparametrization Trick
..
input
.hidden . (sample).
output
.
x
.z.
L
.
qϕ(z | x)
.Id .
pθ(x | z)
Stochastic Compute Graph
..
input
.hidden .
output
.
x
.z. ϵ.
L
.
qϕ(z | x)
.Id .
g
.
pθ(x | z)
Deterministic Compute Graph
The feedforward step involves sam-
pling the random variable z ∼ qϕ(z | x).
However, sampling does not admit a
gradient so back-propagation of gradi-
ents fails.
The Reparametrization Trick replaces
z ∼ qϕ(z | x) with
ˆz = g(ϵ) where ϵ ∼ p(ϵ).
Now the back-propagation path is
through deterministic nodes only.
Of course, our variables are categorical so back-propagation of gradients
fails anyway...
8
Gumbel Softmax Distribution
τ = 0.0
τ = 0.5
τ = 1.0
How to sample from a categorical random variable?
Let z be of dimension k with probabilities (ν1, . . . , νk).
We may sample from z as follows:
z = one-hot
(
arg max
h
{γ1 + ν1, . . . , γk + νk}
)
where γh ∼ Gumbel(0, 1) are IID, h = 1, . . . , k.
One-hot vectors are vertices of the simplex ∆k−1
.
Define a continuous distribution on the interior of the
simplex
y = (y1, . . . , yk) ∈ ∆k−1
, such that
k∑
h=1
yh = 1,
where yh =
e(ln νh+γh)/τ
∑k
j=1 e(ln νj+γj)/τ
, for τ > 0.
As τ → 0 the continuous distribution y converges to
the categorical distribution z.
9
Variational Autoencoder for Categorical Variables
Relax the categorical assumptions of the model in order to obtain a
continuous model on which back-propagation of gradients applies.
..
x
.y. γ.
L
.
Continuous
.
qϕ(y | x)
.Id .
g
.
pθ(x | y)
... τ → 0.
x
. z.
L
.
Categorical
.
qϕ(z | x)
. Id.
pθ(x | z)
Note:
• for τ small: close to categorical but high variance of gradients
• for τ large: far from categorical but low variance of gradients
In practice, start training with large τ and anneal to small τ.
10
Application
Train variational autoencoder to obtain parameters ˆθ, ˆϕ.
Possible approaches for anomaly detection:
• Use qˆϕ(z | x) : x → z for input to a machine learning anomaly detector
• Use pˆθ : x → p ∈ [0, 1] to identify rare events
• Use reconstruction error
x
q ˆϕ
−→ z
p ˆθ
−→ x
as anomaly detector
Other approaches are possible...
11
Questions?
11

More Related Content

What's hot

The world of loss function
The world of loss functionThe world of loss function
The world of loss function
홍배 김
 
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Eun Ji Lee
 
Iclr2016 vaeまとめ
Iclr2016 vaeまとめIclr2016 vaeまとめ
Iclr2016 vaeまとめ
Deep Learning JP
 
Accelerating Random Forests in Scikit-Learn
Accelerating Random Forests in Scikit-LearnAccelerating Random Forests in Scikit-Learn
Accelerating Random Forests in Scikit-Learn
Gilles Louppe
 
Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3
TOMMYLINK1
 
Auto encoding-variational-bayes
Auto encoding-variational-bayesAuto encoding-variational-bayes
Auto encoding-variational-bayes
mehdi Cherti
 
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Universitat Politècnica de Catalunya
 
A Maximum Entropy Approach to the Loss Data Aggregation Problem
A Maximum Entropy Approach to the Loss Data Aggregation ProblemA Maximum Entropy Approach to the Loss Data Aggregation Problem
A Maximum Entropy Approach to the Loss Data Aggregation Problem
Erika G. G.
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
Mark Chang
 
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlowLearning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
Altoros
 
Auto-encoding variational bayes
Auto-encoding variational bayesAuto-encoding variational bayes
Auto-encoding variational bayes
Kyuri Kim
 
Safe and Efficient Off-Policy Reinforcement Learning
Safe and Efficient Off-Policy Reinforcement LearningSafe and Efficient Off-Policy Reinforcement Learning
Safe and Efficient Off-Policy Reinforcement Learning
mooopan
 
Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)
Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)
Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)
Universitat Politècnica de Catalunya
 
Introduction to Big Data Science
Introduction to Big Data ScienceIntroduction to Big Data Science
Introduction to Big Data Science
Albert Bifet
 
Intractable likelihoods
Intractable likelihoodsIntractable likelihoods
Intractable likelihoods
Christian Robert
 
A Gentle Introduction to the EM Algorithm
A Gentle Introduction to the EM AlgorithmA Gentle Introduction to the EM Algorithm
A Gentle Introduction to the EM Algorithm
University of Minnesota, Duluth
 
Tensorflow, deep learning and recurrent neural networks without a ph d
Tensorflow, deep learning and recurrent neural networks   without a ph dTensorflow, deep learning and recurrent neural networks   without a ph d
Tensorflow, deep learning and recurrent neural networks without a ph d
DanielGinot
 
Matching networks for one shot learning
Matching networks for one shot learningMatching networks for one shot learning
Matching networks for one shot learning
Kazuki Fujikawa
 
Additive model and boosting tree
Additive model and boosting treeAdditive model and boosting tree
Additive model and boosting tree
Dong Guo
 

What's hot (20)

The world of loss function
The world of loss functionThe world of loss function
The world of loss function
 
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
 
Iclr2016 vaeまとめ
Iclr2016 vaeまとめIclr2016 vaeまとめ
Iclr2016 vaeまとめ
 
Accelerating Random Forests in Scikit-Learn
Accelerating Random Forests in Scikit-LearnAccelerating Random Forests in Scikit-Learn
Accelerating Random Forests in Scikit-Learn
 
Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3Rabbit challenge 5_dnn3
Rabbit challenge 5_dnn3
 
Auto encoding-variational-bayes
Auto encoding-variational-bayesAuto encoding-variational-bayes
Auto encoding-variational-bayes
 
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
Convolutional Neural Networks (DLAI D5L1 2017 UPC Deep Learning for Artificia...
 
A Maximum Entropy Approach to the Loss Data Aggregation Problem
A Maximum Entropy Approach to the Loss Data Aggregation ProblemA Maximum Entropy Approach to the Loss Data Aggregation Problem
A Maximum Entropy Approach to the Loss Data Aggregation Problem
 
Presentation1
Presentation1Presentation1
Presentation1
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
 
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlowLearning Financial Market Data with Recurrent Autoencoders and TensorFlow
Learning Financial Market Data with Recurrent Autoencoders and TensorFlow
 
Auto-encoding variational bayes
Auto-encoding variational bayesAuto-encoding variational bayes
Auto-encoding variational bayes
 
Safe and Efficient Off-Policy Reinforcement Learning
Safe and Efficient Off-Policy Reinforcement LearningSafe and Efficient Off-Policy Reinforcement Learning
Safe and Efficient Off-Policy Reinforcement Learning
 
Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)
Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)
Word Embeddings (D2L4 Deep Learning for Speech and Language UPC 2017)
 
Introduction to Big Data Science
Introduction to Big Data ScienceIntroduction to Big Data Science
Introduction to Big Data Science
 
Intractable likelihoods
Intractable likelihoodsIntractable likelihoods
Intractable likelihoods
 
A Gentle Introduction to the EM Algorithm
A Gentle Introduction to the EM AlgorithmA Gentle Introduction to the EM Algorithm
A Gentle Introduction to the EM Algorithm
 
Tensorflow, deep learning and recurrent neural networks without a ph d
Tensorflow, deep learning and recurrent neural networks   without a ph dTensorflow, deep learning and recurrent neural networks   without a ph d
Tensorflow, deep learning and recurrent neural networks without a ph d
 
Matching networks for one shot learning
Matching networks for one shot learningMatching networks for one shot learning
Matching networks for one shot learning
 
Additive model and boosting tree
Additive model and boosting treeAdditive model and boosting tree
Additive model and boosting tree
 

Viewers also liked

Saving Environment with IoT: Smart Watering with Predix
Saving Environment with IoT: Smart Watering with PredixSaving Environment with IoT: Smart Watering with Predix
Saving Environment with IoT: Smart Watering with Predix
Altoros
 
A Secure Model of IoT Using Blockchain
A Secure Model of IoT Using BlockchainA Secure Model of IoT Using Blockchain
A Secure Model of IoT Using Blockchain
Altoros
 
67 Weeks of TensorFlow
67 Weeks of TensorFlow67 Weeks of TensorFlow
67 Weeks of TensorFlow
Altoros
 
Security of IoT Data: Implementing Data-Centric Security and User Access Stra...
Security of IoT Data: Implementing Data-Centric Security and User Access Stra...Security of IoT Data: Implementing Data-Centric Security and User Access Stra...
Security of IoT Data: Implementing Data-Centric Security and User Access Stra...
Altoros
 
Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...
Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...
Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...
Altoros
 
2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity
2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity
2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity
Nathan Anderson
 
CernVM-FS for Docker image distribution in Cloud Foundry
CernVM-FS for Docker image distribution in Cloud FoundryCernVM-FS for Docker image distribution in Cloud Foundry
CernVM-FS for Docker image distribution in Cloud Foundry
George Lestaris
 
Cybesecurity of the IoT
Cybesecurity of the IoTCybesecurity of the IoT
Cybesecurity of the IoT
Altoros
 
Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015
Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015
Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015
David Soul
 
Cyber security for children
Cyber security for childrenCyber security for children
Cyber security for children
Avanzo net
 
How does the Cloud Foundry Diego Project Run at Scale?
How does the Cloud Foundry Diego Project Run at Scale?How does the Cloud Foundry Diego Project Run at Scale?
How does the Cloud Foundry Diego Project Run at Scale?
VMware Tanzu
 
Beyond Matching: Applying Data Science Techniques to IOC-based Detection
Beyond Matching: Applying Data Science Techniques to IOC-based DetectionBeyond Matching: Applying Data Science Techniques to IOC-based Detection
Beyond Matching: Applying Data Science Techniques to IOC-based Detection
Alex Pinto
 
The Industrial Internet: Automation and Analytics
The Industrial Internet: Automation and AnalyticsThe Industrial Internet: Automation and Analytics
The Industrial Internet: Automation and Analytics
Altoros
 
European Cyber Security Challenge - Greel National Cyber Security Team
European Cyber Security Challenge - Greel National Cyber Security TeamEuropean Cyber Security Challenge - Greel National Cyber Security Team
European Cyber Security Challenge - Greel National Cyber Security Team
isc2-hellenic
 
Cloud Foundry V2 | Intermediate Deep Dive
Cloud Foundry V2 | Intermediate Deep DiveCloud Foundry V2 | Intermediate Deep Dive
Cloud Foundry V2 | Intermediate Deep DiveKazuto Kusama
 
Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...
Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...
Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...
Alex Pinto
 
Circle of Code with Cloud Foundry
Circle of Code with Cloud FoundryCircle of Code with Cloud Foundry
Circle of Code with Cloud Foundry
Tomohiro Ichimura
 
Image Recognition with TensorFlow
Image Recognition with TensorFlowImage Recognition with TensorFlow
Image Recognition with TensorFlow
Altoros
 
Who Lives in Our Garden?
Who Lives in Our Garden?Who Lives in Our Garden?
Who Lives in Our Garden?
Altoros
 

Viewers also liked (19)

Saving Environment with IoT: Smart Watering with Predix
Saving Environment with IoT: Smart Watering with PredixSaving Environment with IoT: Smart Watering with Predix
Saving Environment with IoT: Smart Watering with Predix
 
A Secure Model of IoT Using Blockchain
A Secure Model of IoT Using BlockchainA Secure Model of IoT Using Blockchain
A Secure Model of IoT Using Blockchain
 
67 Weeks of TensorFlow
67 Weeks of TensorFlow67 Weeks of TensorFlow
67 Weeks of TensorFlow
 
Security of IoT Data: Implementing Data-Centric Security and User Access Stra...
Security of IoT Data: Implementing Data-Centric Security and User Access Stra...Security of IoT Data: Implementing Data-Centric Security and User Access Stra...
Security of IoT Data: Implementing Data-Centric Security and User Access Stra...
 
Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...
Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...
Unified Analytics in GE’s Predix for the IIoT: Tying Operational Technology t...
 
2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity
2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity
2016 ISACA NACACS - Audit As An Impact Player For Cybersecurity
 
CernVM-FS for Docker image distribution in Cloud Foundry
CernVM-FS for Docker image distribution in Cloud FoundryCernVM-FS for Docker image distribution in Cloud Foundry
CernVM-FS for Docker image distribution in Cloud Foundry
 
Cybesecurity of the IoT
Cybesecurity of the IoTCybesecurity of the IoT
Cybesecurity of the IoT
 
Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015
Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015
Cloud Foundry Diego: The New Cloud Runtime - CloudOpen Europe Talk 2015
 
Cyber security for children
Cyber security for childrenCyber security for children
Cyber security for children
 
How does the Cloud Foundry Diego Project Run at Scale?
How does the Cloud Foundry Diego Project Run at Scale?How does the Cloud Foundry Diego Project Run at Scale?
How does the Cloud Foundry Diego Project Run at Scale?
 
Beyond Matching: Applying Data Science Techniques to IOC-based Detection
Beyond Matching: Applying Data Science Techniques to IOC-based DetectionBeyond Matching: Applying Data Science Techniques to IOC-based Detection
Beyond Matching: Applying Data Science Techniques to IOC-based Detection
 
The Industrial Internet: Automation and Analytics
The Industrial Internet: Automation and AnalyticsThe Industrial Internet: Automation and Analytics
The Industrial Internet: Automation and Analytics
 
European Cyber Security Challenge - Greel National Cyber Security Team
European Cyber Security Challenge - Greel National Cyber Security TeamEuropean Cyber Security Challenge - Greel National Cyber Security Team
European Cyber Security Challenge - Greel National Cyber Security Team
 
Cloud Foundry V2 | Intermediate Deep Dive
Cloud Foundry V2 | Intermediate Deep DiveCloud Foundry V2 | Intermediate Deep Dive
Cloud Foundry V2 | Intermediate Deep Dive
 
Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...
Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...
Secure Because Math: A Deep-Dive on Machine Learning-Based Monitoring (#Secur...
 
Circle of Code with Cloud Foundry
Circle of Code with Cloud FoundryCircle of Code with Cloud Foundry
Circle of Code with Cloud Foundry
 
Image Recognition with TensorFlow
Image Recognition with TensorFlowImage Recognition with TensorFlow
Image Recognition with TensorFlow
 
Who Lives in Our Garden?
Who Lives in Our Garden?Who Lives in Our Garden?
Who Lives in Our Garden?
 

Similar to Deep Learning for Cyber Security

XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
Erlangen Artificial Intelligence & Machine Learning Meetup
 
從 VAE 走向深度學習新理論
從 VAE 走向深度學習新理論從 VAE 走向深度學習新理論
從 VAE 走向深度學習新理論
岳華 杜
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
The Statistical and Applied Mathematical Sciences Institute
 
Bayesian Deep Learning
Bayesian Deep LearningBayesian Deep Learning
Bayesian Deep Learning
RayKim51
 
Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...
Frank Nielsen
 
Delayed acceptance for Metropolis-Hastings algorithms
Delayed acceptance for Metropolis-Hastings algorithmsDelayed acceptance for Metropolis-Hastings algorithms
Delayed acceptance for Metropolis-Hastings algorithms
Christian Robert
 
Cuckoo Search Algorithm: An Introduction
Cuckoo Search Algorithm: An IntroductionCuckoo Search Algorithm: An Introduction
Cuckoo Search Algorithm: An Introduction
Xin-She Yang
 
"Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof...
"Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof..."Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof...
"Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof...
Paris Women in Machine Learning and Data Science
 
Statement of stochastic programming problems
Statement of stochastic programming problemsStatement of stochastic programming problems
Statement of stochastic programming problems
SSA KPI
 
Options Portfolio Selection
Options Portfolio SelectionOptions Portfolio Selection
Options Portfolio Selection
guasoni
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
Valentin De Bortoli
 
pptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspacespptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspacesbutest
 
pptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspacespptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspacesbutest
 
Asynchronous Stochastic Optimization, New Analysis and Algorithms
Asynchronous Stochastic Optimization, New Analysis and AlgorithmsAsynchronous Stochastic Optimization, New Analysis and Algorithms
Asynchronous Stochastic Optimization, New Analysis and Algorithms
Fabian Pedregosa
 
Stratified sampling and resampling for approximate Bayesian computation
Stratified sampling and resampling for approximate Bayesian computationStratified sampling and resampling for approximate Bayesian computation
Stratified sampling and resampling for approximate Bayesian computation
Umberto Picchini
 
Ml mle_bayes
Ml  mle_bayesMl  mle_bayes
Ml mle_bayesPhong Vo
 
block-mdp-masters-defense.pdf
block-mdp-masters-defense.pdfblock-mdp-masters-defense.pdf
block-mdp-masters-defense.pdf
Junghyun Lee
 
Machine Learning 1
Machine Learning 1Machine Learning 1
Machine Learning 1
cairo university
 
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
Huang Po Chun
 

Similar to Deep Learning for Cyber Security (20)

XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
XGBoostLSS - An extension of XGBoost to probabilistic forecasting, Alexander ...
 
從 VAE 走向深度學習新理論
從 VAE 走向深度學習新理論從 VAE 走向深度學習新理論
從 VAE 走向深度學習新理論
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
Bayesian Deep Learning
Bayesian Deep LearningBayesian Deep Learning
Bayesian Deep Learning
 
Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...Pattern learning and recognition on statistical manifolds: An information-geo...
Pattern learning and recognition on statistical manifolds: An information-geo...
 
Delayed acceptance for Metropolis-Hastings algorithms
Delayed acceptance for Metropolis-Hastings algorithmsDelayed acceptance for Metropolis-Hastings algorithms
Delayed acceptance for Metropolis-Hastings algorithms
 
Cuckoo Search Algorithm: An Introduction
Cuckoo Search Algorithm: An IntroductionCuckoo Search Algorithm: An Introduction
Cuckoo Search Algorithm: An Introduction
 
"Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof...
"Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof..."Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof...
"Let us talk about output features! by Florence d’Alché-Buc, LTCI & Full Prof...
 
Statement of stochastic programming problems
Statement of stochastic programming problemsStatement of stochastic programming problems
Statement of stochastic programming problems
 
Options Portfolio Selection
Options Portfolio SelectionOptions Portfolio Selection
Options Portfolio Selection
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
pptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspacespptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspaces
 
pptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspacespptx - Psuedo Random Generator for Halfspaces
pptx - Psuedo Random Generator for Halfspaces
 
Asynchronous Stochastic Optimization, New Analysis and Algorithms
Asynchronous Stochastic Optimization, New Analysis and AlgorithmsAsynchronous Stochastic Optimization, New Analysis and Algorithms
Asynchronous Stochastic Optimization, New Analysis and Algorithms
 
Stratified sampling and resampling for approximate Bayesian computation
Stratified sampling and resampling for approximate Bayesian computationStratified sampling and resampling for approximate Bayesian computation
Stratified sampling and resampling for approximate Bayesian computation
 
Ml mle_bayes
Ml  mle_bayesMl  mle_bayes
Ml mle_bayes
 
talk MCMC & SMC 2004
talk MCMC & SMC 2004talk MCMC & SMC 2004
talk MCMC & SMC 2004
 
block-mdp-masters-defense.pdf
block-mdp-masters-defense.pdfblock-mdp-masters-defense.pdf
block-mdp-masters-defense.pdf
 
Machine Learning 1
Machine Learning 1Machine Learning 1
Machine Learning 1
 
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
Divide_and_Contrast__Source_free_Domain_Adaptation_via_Adaptive_Contrastive_L...
 

More from Altoros

Maturing with Kubernetes
Maturing with KubernetesMaturing with Kubernetes
Maturing with Kubernetes
Altoros
 
Kubernetes Platform Readiness and Maturity Assessment
Kubernetes Platform Readiness and Maturity AssessmentKubernetes Platform Readiness and Maturity Assessment
Kubernetes Platform Readiness and Maturity Assessment
Altoros
 
Journey Through Four Stages of Kubernetes Deployment Maturity
Journey Through Four Stages of Kubernetes Deployment MaturityJourney Through Four Stages of Kubernetes Deployment Maturity
Journey Through Four Stages of Kubernetes Deployment Maturity
Altoros
 
SGX: Improving Privacy, Security, and Trust Across Blockchain Networks
SGX: Improving Privacy, Security, and Trust Across Blockchain NetworksSGX: Improving Privacy, Security, and Trust Across Blockchain Networks
SGX: Improving Privacy, Security, and Trust Across Blockchain Networks
Altoros
 
Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...
Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...
Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...
Altoros
 
A Zero-Knowledge Proof: Improving Privacy on a Blockchain
A Zero-Knowledge Proof:  Improving Privacy on a BlockchainA Zero-Knowledge Proof:  Improving Privacy on a Blockchain
A Zero-Knowledge Proof: Improving Privacy on a Blockchain
Altoros
 
Crap. Your Big Data Kitchen Is Broken.
Crap. Your Big Data Kitchen Is Broken.Crap. Your Big Data Kitchen Is Broken.
Crap. Your Big Data Kitchen Is Broken.
Altoros
 
Containers and Kubernetes
Containers and KubernetesContainers and Kubernetes
Containers and Kubernetes
Altoros
 
Distributed Ledger Technology for Over-the-Counter Trading
Distributed Ledger Technology for Over-the-Counter TradingDistributed Ledger Technology for Over-the-Counter Trading
Distributed Ledger Technology for Over-the-Counter Trading
Altoros
 
5-Step Deployment of Hyperledger Fabric on Multiple Nodes
5-Step Deployment of Hyperledger Fabric on Multiple Nodes5-Step Deployment of Hyperledger Fabric on Multiple Nodes
5-Step Deployment of Hyperledger Fabric on Multiple Nodes
Altoros
 
Deploying Kubernetes on GCP with Kubespray
Deploying Kubernetes on GCP with KubesprayDeploying Kubernetes on GCP with Kubespray
Deploying Kubernetes on GCP with Kubespray
Altoros
 
UAA for Kubernetes
UAA for KubernetesUAA for Kubernetes
UAA for Kubernetes
Altoros
 
Troubleshooting .NET Applications on Cloud Foundry
Troubleshooting .NET Applications on Cloud FoundryTroubleshooting .NET Applications on Cloud Foundry
Troubleshooting .NET Applications on Cloud Foundry
Altoros
 
Continuous Integration and Deployment with Jenkins for PCF
Continuous Integration and Deployment with Jenkins for PCFContinuous Integration and Deployment with Jenkins for PCF
Continuous Integration and Deployment with Jenkins for PCF
Altoros
 
How to Never Leave Your Deployment Unattended
How to Never Leave Your Deployment UnattendedHow to Never Leave Your Deployment Unattended
How to Never Leave Your Deployment Unattended
Altoros
 
Cloud Foundry Monitoring How-To: Collecting Metrics and Logs
Cloud Foundry Monitoring How-To: Collecting Metrics and LogsCloud Foundry Monitoring How-To: Collecting Metrics and Logs
Cloud Foundry Monitoring How-To: Collecting Metrics and Logs
Altoros
 
Smart Baggage Tracking: End-to-End Sensor-Based Solution
Smart Baggage Tracking: End-to-End Sensor-Based SolutionSmart Baggage Tracking: End-to-End Sensor-Based Solution
Smart Baggage Tracking: End-to-End Sensor-Based Solution
Altoros
 
Navigating the Ecosystem of Pivotal Cloud Foundry Tiles
Navigating the Ecosystem of Pivotal Cloud Foundry TilesNavigating the Ecosystem of Pivotal Cloud Foundry Tiles
Navigating the Ecosystem of Pivotal Cloud Foundry Tiles
Altoros
 
AI as a Catalyst for IoT
AI as a Catalyst for IoTAI as a Catalyst for IoT
AI as a Catalyst for IoT
Altoros
 
Over-Engineering: Causes, Symptoms, and Treatment
Over-Engineering: Causes, Symptoms, and TreatmentOver-Engineering: Causes, Symptoms, and Treatment
Over-Engineering: Causes, Symptoms, and Treatment
Altoros
 

More from Altoros (20)

Maturing with Kubernetes
Maturing with KubernetesMaturing with Kubernetes
Maturing with Kubernetes
 
Kubernetes Platform Readiness and Maturity Assessment
Kubernetes Platform Readiness and Maturity AssessmentKubernetes Platform Readiness and Maturity Assessment
Kubernetes Platform Readiness and Maturity Assessment
 
Journey Through Four Stages of Kubernetes Deployment Maturity
Journey Through Four Stages of Kubernetes Deployment MaturityJourney Through Four Stages of Kubernetes Deployment Maturity
Journey Through Four Stages of Kubernetes Deployment Maturity
 
SGX: Improving Privacy, Security, and Trust Across Blockchain Networks
SGX: Improving Privacy, Security, and Trust Across Blockchain NetworksSGX: Improving Privacy, Security, and Trust Across Blockchain Networks
SGX: Improving Privacy, Security, and Trust Across Blockchain Networks
 
Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...
Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...
Using the Cloud Foundry and Kubernetes Stack as a Part of a Blockchain CI/CD ...
 
A Zero-Knowledge Proof: Improving Privacy on a Blockchain
A Zero-Knowledge Proof:  Improving Privacy on a BlockchainA Zero-Knowledge Proof:  Improving Privacy on a Blockchain
A Zero-Knowledge Proof: Improving Privacy on a Blockchain
 
Crap. Your Big Data Kitchen Is Broken.
Crap. Your Big Data Kitchen Is Broken.Crap. Your Big Data Kitchen Is Broken.
Crap. Your Big Data Kitchen Is Broken.
 
Containers and Kubernetes
Containers and KubernetesContainers and Kubernetes
Containers and Kubernetes
 
Distributed Ledger Technology for Over-the-Counter Trading
Distributed Ledger Technology for Over-the-Counter TradingDistributed Ledger Technology for Over-the-Counter Trading
Distributed Ledger Technology for Over-the-Counter Trading
 
5-Step Deployment of Hyperledger Fabric on Multiple Nodes
5-Step Deployment of Hyperledger Fabric on Multiple Nodes5-Step Deployment of Hyperledger Fabric on Multiple Nodes
5-Step Deployment of Hyperledger Fabric on Multiple Nodes
 
Deploying Kubernetes on GCP with Kubespray
Deploying Kubernetes on GCP with KubesprayDeploying Kubernetes on GCP with Kubespray
Deploying Kubernetes on GCP with Kubespray
 
UAA for Kubernetes
UAA for KubernetesUAA for Kubernetes
UAA for Kubernetes
 
Troubleshooting .NET Applications on Cloud Foundry
Troubleshooting .NET Applications on Cloud FoundryTroubleshooting .NET Applications on Cloud Foundry
Troubleshooting .NET Applications on Cloud Foundry
 
Continuous Integration and Deployment with Jenkins for PCF
Continuous Integration and Deployment with Jenkins for PCFContinuous Integration and Deployment with Jenkins for PCF
Continuous Integration and Deployment with Jenkins for PCF
 
How to Never Leave Your Deployment Unattended
How to Never Leave Your Deployment UnattendedHow to Never Leave Your Deployment Unattended
How to Never Leave Your Deployment Unattended
 
Cloud Foundry Monitoring How-To: Collecting Metrics and Logs
Cloud Foundry Monitoring How-To: Collecting Metrics and LogsCloud Foundry Monitoring How-To: Collecting Metrics and Logs
Cloud Foundry Monitoring How-To: Collecting Metrics and Logs
 
Smart Baggage Tracking: End-to-End Sensor-Based Solution
Smart Baggage Tracking: End-to-End Sensor-Based SolutionSmart Baggage Tracking: End-to-End Sensor-Based Solution
Smart Baggage Tracking: End-to-End Sensor-Based Solution
 
Navigating the Ecosystem of Pivotal Cloud Foundry Tiles
Navigating the Ecosystem of Pivotal Cloud Foundry TilesNavigating the Ecosystem of Pivotal Cloud Foundry Tiles
Navigating the Ecosystem of Pivotal Cloud Foundry Tiles
 
AI as a Catalyst for IoT
AI as a Catalyst for IoTAI as a Catalyst for IoT
AI as a Catalyst for IoT
 
Over-Engineering: Causes, Symptoms, and Treatment
Over-Engineering: Causes, Symptoms, and TreatmentOver-Engineering: Causes, Symptoms, and Treatment
Over-Engineering: Causes, Symptoms, and Treatment
 

Recently uploaded

Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
Fwdays
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
Bhaskar Mitra
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
Abida Shariff
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 

Recently uploaded (20)

Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 

Deep Learning for Cyber Security

  • 1. Deep Learning for Cyber Security . Steven Hutt steven.c.hutt@gmail.com 28 February, 2017
  • 2. Cyber Security www.dropbox.gov Why now? • DNC, Sony, Yahoo, ... • attack vectors constantly changing • static detection approaches failing • large amounts of data • Deep Learning for anomaly detection • corporate / government motivated 1
  • 3. The Challenge Can we apply Deep Learning to Cyber Security and better identify malicious network traffic? Reasons to be Optimistic: • Plenty of data • Good progress in general area of unsupervised feature selection • Good progress in general area of anomaly detection • Very topical subject - so that's good! Reasons to be Skeptical: • Practical usage requires very low false positive rate • Essentially no labelled data • Data is a hybrid of categorical (mostly) and numeric (some) • Very topical subject - so why are there so few commercial successes? Reasons to try: • potentially huge market • it's fun 2
  • 4. Network Flow: the unit of data A network flow is a record of the information exchanged via packets between a source and a destination machine during the course of the network protocol session. ipv4Source 192.104.50.16 hasAttach True ipv4Dest 147.135.57.43 sizeAttach 87 portSource 80 mimeType avi portDest 1639 numAttach 1 latitude -5.31858 cookie 'name=kpl; expires=...' longitude 81.52040 subject 'Re: meeting' duration 13.87 searchString 'free beer' timeStamp 1486034657716 urlString 'https://test-cloud-p...' Network flow values are a hybrid of categorical, numerical and text data. Deep Learning for numerical and text data has been extensively developed. Here we focus on Deep Learning for categorical data. 3
  • 5. Unsupervised Anomaly Detection We attempt to fit a probability distribution to the data {xk}N k=1. Many approaches are possible. We focus here on generative models: ..z. x . pθ(z). pθ(x) . prior. likelihood . marginal . posterior . pθ(x | z) . pθ(z | x) Maximize log-likelihood of data: pθ(x) = ∑ z pθ(x | z)pθ(z) ˆθ = arg min θ N∑ k=1 log ∑ z pθ(xk | z)pθ(z) Possible uses of generative model: • A data point x is labelled anomalous if pˆθ(x) is below some threshold. • The posterior pˆθ(z | x) determines unsupervised feature extraction z of the data x. Features z can then be used in subsequent anomaly detection model. 4
  • 6. Categorical Distributions Deep Learning for categorical data has been less studied than for numerical or text data, so we focus on modelling multivariate categorical distributions. Let x = {x1, . . . , xp} be categorical variables with xj ∈ {1, . . . , dj}, j = 1, . . . p. Let π be a probability distribution on x: πc1...cp = P(x1 = c1, . . . , xp = cp), Then there exists: 1. an integer k > 0 2. a mixing variable z ∈ {1, . . . , k} with distribution ν = (ν1, . . . , νk) 3. a set of independent distributions ψ (j) hcj = P(xj = cj | z = h) such that πc1...cp = P(x1 = c1, . . . , xp = cp) = k∑ h=1 νk p ∏ j=1 ψ (j) hcj . In other words, every multivariate categorical distribution is a mixture of multivariate categorical distributions with independent marginals. 5
  • 7. Problems While the mixture representation result is encouraging there are several challenges: 1. Direct likelihood maximization is computationally very expensive 2. Stochastic Gradient Descent is not possible as variables are discrete 3. The size k of the mixing variable is geometric in the dimension p In order to address these challenges, we will utilize the following: 1. variational inference for approximate likelihood maximization 2. Gumbel softmax to relax categorical variables to continuous variables 3. Dirichlet processes to incorporate k as part of the inference 6
  • 8. Variational Autoencoders in a Nutshell Recall we wish to compute ˆθ = arg min θ N∑ k=1 log ∑ z pθ(xk | z)pθ(z) so we need to efficiently compute ∑ z pθ(xk | z)pθ(z). We can (badly) approximate by sampling: ∑ z pθ(xk | z)pθ(z) ≃ M∑ i=1 pθ(xk | zi), where zi ∼ pθ(z) But most of the time pθ(xk | zi) ≃ 0 so sample from zi ∼ pθ(z | xk) instead. But pθ(z | xk) is the wrong distribution and is unknown... ... so we learn an approximation qϕ(z | xk) to the unknown pθ(z | xk) ... and account for the wrong distribution via a likelihood upper bound: Lθ,ϕ(xk) = −DKL(qϕ(z | xk)||pθ(z)) regularization term + Eqϕ (log pθ(xk | z)) reconstruction term Think of qϕ(z | x) : x → z as an encoder and pθ(x | z) : z → x as a decoder. 7
  • 9. The Reparametrization Trick .. input .hidden . (sample). output . x .z. L . qϕ(z | x) .Id . pθ(x | z) Stochastic Compute Graph .. input .hidden . output . x .z. ϵ. L . qϕ(z | x) .Id . g . pθ(x | z) Deterministic Compute Graph The feedforward step involves sam- pling the random variable z ∼ qϕ(z | x). However, sampling does not admit a gradient so back-propagation of gradi- ents fails. The Reparametrization Trick replaces z ∼ qϕ(z | x) with ˆz = g(ϵ) where ϵ ∼ p(ϵ). Now the back-propagation path is through deterministic nodes only. Of course, our variables are categorical so back-propagation of gradients fails anyway... 8
  • 10. Gumbel Softmax Distribution τ = 0.0 τ = 0.5 τ = 1.0 How to sample from a categorical random variable? Let z be of dimension k with probabilities (ν1, . . . , νk). We may sample from z as follows: z = one-hot ( arg max h {γ1 + ν1, . . . , γk + νk} ) where γh ∼ Gumbel(0, 1) are IID, h = 1, . . . , k. One-hot vectors are vertices of the simplex ∆k−1 . Define a continuous distribution on the interior of the simplex y = (y1, . . . , yk) ∈ ∆k−1 , such that k∑ h=1 yh = 1, where yh = e(ln νh+γh)/τ ∑k j=1 e(ln νj+γj)/τ , for τ > 0. As τ → 0 the continuous distribution y converges to the categorical distribution z. 9
  • 11. Variational Autoencoder for Categorical Variables Relax the categorical assumptions of the model in order to obtain a continuous model on which back-propagation of gradients applies. .. x .y. γ. L . Continuous . qϕ(y | x) .Id . g . pθ(x | y) ... τ → 0. x . z. L . Categorical . qϕ(z | x) . Id. pθ(x | z) Note: • for τ small: close to categorical but high variance of gradients • for τ large: far from categorical but low variance of gradients In practice, start training with large τ and anneal to small τ. 10
  • 12. Application Train variational autoencoder to obtain parameters ˆθ, ˆϕ. Possible approaches for anomaly detection: • Use qˆϕ(z | x) : x → z for input to a machine learning anomaly detector • Use pˆθ : x → p ∈ [0, 1] to identify rare events • Use reconstruction error x q ˆϕ −→ z p ˆθ −→ x as anomaly detector Other approaches are possible... 11