SlideShare a Scribd company logo
Pattern Recognition
and Applications Lab
	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  
	
  
University
of Cagliari, Italy
	
  
Department of
Electrical and Electronic
Engineering
Evasion attacks against machine learning
at test time
Ba#sta	
  Biggio	
  (1)	
  
Igino	
  Corona	
  (1),	
  Davide	
  Maiorca	
  (1),	
  Blaine	
  Nelson	
  (3),	
  Nedim	
  Šrndić	
  (2),	
  
Pavel	
  Laskov	
  (2),	
  Giorgio	
  Giacinto	
  (1),	
  and	
  Fabio	
  Roli	
  (1)	
  
	
  
(1)	
  University	
  of	
  Cagliari	
  (IT);	
  (2)	
  University	
  of	
  Tuebingen	
  (GE);	
  (3)	
  University	
  of	
  Postdam	
  (GE)	
  
 
http://pralab.diee.unica.it
Machine learning in adversarial settings
•  Machine learning in computer security
–  spam filtering, intrusion detection, malware detection
legitimate
malicious
x1	
  
x2	
   f(x)
2	
  
 
http://pralab.diee.unica.it
Machine learning in adversarial settings
•  Machine learning in computer security
–  spam filtering, intrusion detection, malware detection
•  Adversaries manipulate samples at test time to evade detection
legitimate
malicious
x1	
  
x2	
   f(x)
3	
  
Trading alert!
We see a run starting to happen.
It’s just beginning of 1 week
promotion
…Tr@ding al3rt!
We see a run starting to happen.
It’s just beginning of 1 week
pr0m0ti0n
…
 
http://pralab.diee.unica.it
Our work
Problem: can machine learning be secure? (1)
•  Framework for proactive security evaluation of ML algorithms (2)
Adversary model
•  Goal of the attack
•  Knowledge of the attacked system
•  Capability of manipulating data
•  Attack strategy as an optimization problem
4	
  
Bounded adversary!
(1)  M.	
  Barreno,	
  B.	
  Nelson,	
  R.	
  Sears,	
  A.	
  D.	
  Joseph,	
  and	
  J.	
  D.	
  Tygar.	
  Can	
  
machine	
  learning	
  be	
  secure?	
  ASIACCS	
  2006	
  
(2)  B.	
  Biggio,	
  G.	
  Fumera,	
  F.	
  Roli.	
  Security	
  evaluaVon	
  of	
  paWern	
  classifiers	
  
under	
  aWack.	
  IEEE	
  Trans.	
  on	
  Knowl.	
  and	
  Data	
  Engineering,	
  2013	
  
In	
  this	
  work	
  we	
  exploit	
  our	
  framework	
  for	
  
security	
  evaluaVon	
  against	
  evasion	
  a)acks!	
  
 
http://pralab.diee.unica.it
Bounding the adversary’s capability
•  Cost of manipulations
–  Spam: message readability
•  Encoded by a distance function in feature space (L1-norm)
–  e.g., number of words that are modified in spam emails
5	
  
d (x, !x ) ≤ dmax
x2	
  
x1	
  
f(x)
Bounded by a maximum value
x
Feasible domain
x '
We	
  will	
  evaluate	
  classifier	
  
performance	
  vs.	
  increasing	
  dmax	
  
 
http://pralab.diee.unica.it
Gradient-descent evasion attacks
•  Goal: maximum-confidence evasion
•  Knowledge: perfect
•  Attack strategy:
•  Non-linear, constrained optimization
–  Gradient descent: approximate
solution for smooth functions
•  Gradients of g(x) can be analytically
computed in many cases
–  SVMs, Neural networks
6	
  
−2−1.5−1−0.500.51
x
f (x) = sign g(x)( )=
+1, malicious
−1, legitimate
"
#
$
%$
min
x'
g(x')
s.t. d(x, x') ≤ dmax
x '
 
http://pralab.diee.unica.it
Computing descent directions
Support vector machines
Neural networks
7	
  
x1	
  
xd	
  
δ1	
  
δk	
  
δm	
  
xf	
   g(x)	
  
w1	
  
wk	
  
wm	
  
v11	
  
vmd	
  
vk1	
  
……
……
g(x) = αi yik(x,
i
∑ xi )+ b, ∇g(x) = αi yi∇k(x, xi )
i
∑
g(x) = 1+exp − wkδk (x)
k=1
m
∑
#
$
%
&
'
(
)
*
+
,
-
.
−1
∂g(x)
∂xf
= g(x) 1− g(x)( ) wkδk (x) 1−δk (x)( )vkf
k=1
m
∑
RBF kernel gradient: ∇k (x,xi
) = −2γ exp −γ || x − xi
||2
{ }(x − xi
)
 
http://pralab.diee.unica.it
g(x) − λ p(x|yc=−1), λ=0
−4 −3 −2 −1 0 1 2 3 4
−4
−2
0
2
4
−1
−0.5
0
0.5
1
•  Problem: greedily min. g(x) may not lead to classifier evasion!
•  Solution: adding a mimicry component that attracts the attack
samples towards samples classified as legitimate
Density-augmented gradient-descent
Mimicry component
(Kernel Density Estimator)
8	
  
g(x) − λ p(x|yc=−1), λ=20
−4 −3 −2 −1 0 1 2 3 4
−4
−2
0
2
4
−4.5
−4
−3.5
−3
−2.5
−2
−1.5
−1
Now	
  all	
  the	
  aWack	
  samples	
  evade	
  
the	
  classifier!	
  
Some	
  aWack	
  samples	
  may	
  not	
  evade	
  
the	
  classifier!	
  	
  
min
x'
g(x')− λp(x' | yc
= −1)
s.t. d(x, x') ≤ dmax
 
http://pralab.diee.unica.it
Density-augmented gradient-descent
9	
  
∇p(x | yc
= −1) = −
2
nh
exp −
|| x − xi ||2
h
#
$
%
&
'
( x − xi( )i|yi
c=−1∑KDE	
  gradient	
  (RBF	
  kernel):	
  
 
http://pralab.diee.unica.it
An example on MNIST handwritten digits
10	
  
•  Linear SVM, 3 vs 7. Features: pixel values.
Before attack (3 vs 7)
5 10 15 20 25
5
10
15
20
25
After attack, g(x)=0
5 10 15 20 25
5
10
15
20
25
After attack, last iter.
5 10 15 20 25
5
10
15
20
25
0 500
−2
−1
0
1
2
g(x)
number of iterations
Without mimicry
λ = 0
dmax
5000
Before attack (3 vs 7)
5 10 15 20 25
5
10
15
20
25
After attack, g(x)=0
5 10 15 20 25
5
10
15
20
25
After attack, last iter.
5 10 15 20 25
5
10
15
20
25
0 500
−2
−1
0
1
2
g(x)
number of iterations
With mimicry
λ = 10
dmax
5000
 
http://pralab.diee.unica.it
Bounding the adversary’s knowledge
Limited knowledge attacks
•  Only feature representation and learning algorithm are known
•  Surrogate data sampled from the same distribution as the
classifier’s training data
•  Classifier’s feedback to label surrogate data
11	
  
PD(X,Y)data	
  
Surrogate
training data
f(x)
Send queries
Get labels
Learn
surrogate
classifier
f’(x)
 
http://pralab.diee.unica.it
Experiments on PDF malware detection
•  PDF: hierarchy of interconnected objects (keyword/value pairs)
•  Adversary’s capability
–  adding up to dmax objects to the PDF
–  removing objects may
compromise the PDF file
(and embedded malware code)!
12	
  
/Type 	
   	
  2	
  
/Page 	
   	
  1	
  
/Encoding 	
  1	
  
…	
  
13	
  0	
  obj	
  
<<	
  /Kids	
  [	
  1	
  0	
  R	
  11	
  0	
  R	
  ]	
  
/Type	
  /Page	
  
...	
  >>	
  end	
  obj	
  
17	
  0	
  obj	
  
<<	
  /Type	
  /Encoding	
  
/Differences	
  [	
  0	
  /C0032	
  ]	
  >>	
  
endobj	
  
	
  
Features:	
  keyword	
  count	
  
min
x'
g(x')− λp(x' | y = −1)
s.t. d(x, x') ≤ dmax
x ≤ x'
 
http://pralab.diee.unica.it
0 10 20 30 40 50
0
0.2
0.4
0.6
0.8
1
dmax
FN
SVM (Linear), λ=0
PK (C=1)
LK (C=1)
Experiments on PDF malware detection
Linear SVM
13	
  
0 10 20 30 40 50
0
0.2
0.4
0.6
0.8
1
SVM (linear) − C=1, λ=500
dmax
FN
PK
LK
•  Dataset: 500 malware samples (Contagio), 500 benign (Internet)
–  5-fold cross-validation
–  Targeted (surrogate) classifier trained on 500 (100) samples
•  Evasion rate (FN) at FP=1% vs max. number of added keywords
–  Perfect knowledge (PK); Limited knowledge (LK)
Without mimicry
λ = 0
With mimicry
λ = 500
 
http://pralab.diee.unica.it
Experiments on PDF malware detection
SVM with RBF kernel, Neural Network
14	
  
0 10 20 30 40 50
0
0.2
0.4
0.6
0.8
1
Neural Netw. − m=5,λ=500
dmax
FN
PK
LK
0 10 20 30 40 50
0
0.2
0.4
0.6
0.8
1
SVM (RBF) − C=1, γ=1, λ=500
dmax
FN
PK
LK
0 10 20 30 40 50
0
0.2
0.4
0.6
0.8
1
dmax
FN
SVM (RBF), λ=0
PK (C=1)
LK (C=1)
0 10 20 30 40 50
0
0.2
0.4
0.6
0.8
1
dmax
FN
Neural Netw., λ=0
PK (C=1)
LK (C=1)
(m=5)
(m=5)
 
http://pralab.diee.unica.it
Conclusions and future work
•  Related work. Near-optimal evasion of linear and convex-
inducing classifiers (1,2)
•  Our work. Linear and non-linear classifiers can be highly
vulnerable to well-crafted evasion attacks
–  … even under limited attacker’s knowledge
•  Future work
–  Evasion of non-differentiable decision functions (decision trees)
–  Surrogate data: how to query more efficiently the targeted classifier?
–  Practical evasion: feature representation partially known or difficult to
reverse-engineer
–  Securing learning: game theory to model classifier vs. adversary
15	
  
(1)  D.	
  Lowd	
  and	
  C.	
  Meek.	
  Adversarial	
  learning.	
  ACM	
  SIGKDD,	
  2005.	
  
(2)  B.	
  Nelson,	
  B.	
  I.	
  Rubinstein,	
  L.	
  Huang,	
  A.	
  D.	
  Joseph,	
  S.	
  J.	
  Lee,	
  S.	
  Rao,	
  and	
  J.	
  D.	
  
Tygar.	
  Query	
  strategies	
  for	
  evading	
  convex-­‐inducing	
  classifiers.	
  JMLR,	
  2012.	
  
 
http://pralab.diee.unica.it
?	
  
16	
  
	
  
Any	
  ques@ons	
  Thanks	
  for	
  your	
  aWenVon!	
  

More Related Content

What's hot

Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Pluribus One
 
Machine Learning under Attack: Vulnerability Exploitation and Security Measures
Machine Learning under Attack: Vulnerability Exploitation and Security MeasuresMachine Learning under Attack: Vulnerability Exploitation and Security Measures
Machine Learning under Attack: Vulnerability Exploitation and Security Measures
Pluribus One
 
Research of adversarial example on a deep neural network
Research of adversarial example on a deep neural networkResearch of adversarial example on a deep neural network
Research of adversarial example on a deep neural network
NAVER Engineering
 
Automated In-memory Malware/Rootkit Detection via Binary Analysis and Machin...
Automated In-memory Malware/Rootkit  Detection via Binary Analysis and Machin...Automated In-memory Malware/Rootkit  Detection via Binary Analysis and Machin...
Automated In-memory Malware/Rootkit Detection via Binary Analysis and Machin...
Malachi Jones
 
Self-learning systems for cyber security
Self-learning systems for cyber securitySelf-learning systems for cyber security
Self-learning systems for cyber security
Kim Hammar
 
“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...
“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...
“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...
Edge AI and Vision Alliance
 
Universal Adversarial Perturbation
Universal Adversarial PerturbationUniversal Adversarial Perturbation
Universal Adversarial Perturbation
Hyunwoo Kim
 
Using classifiers to compute similarities between face images. Prof. Lior Wol...
Using classifiers to compute similarities between face images. Prof. Lior Wol...Using classifiers to compute similarities between face images. Prof. Lior Wol...
Using classifiers to compute similarities between face images. Prof. Lior Wol...
yaevents
 
Strata San Jose 2016 - Reduce False Positives in Security
Strata San Jose 2016 - Reduce False Positives in Security Strata San Jose 2016 - Reduce False Positives in Security
Strata San Jose 2016 - Reduce False Positives in Security
Ram Shankar Siva Kumar
 

What's hot (9)

Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub...
 
Machine Learning under Attack: Vulnerability Exploitation and Security Measures
Machine Learning under Attack: Vulnerability Exploitation and Security MeasuresMachine Learning under Attack: Vulnerability Exploitation and Security Measures
Machine Learning under Attack: Vulnerability Exploitation and Security Measures
 
Research of adversarial example on a deep neural network
Research of adversarial example on a deep neural networkResearch of adversarial example on a deep neural network
Research of adversarial example on a deep neural network
 
Automated In-memory Malware/Rootkit Detection via Binary Analysis and Machin...
Automated In-memory Malware/Rootkit  Detection via Binary Analysis and Machin...Automated In-memory Malware/Rootkit  Detection via Binary Analysis and Machin...
Automated In-memory Malware/Rootkit Detection via Binary Analysis and Machin...
 
Self-learning systems for cyber security
Self-learning systems for cyber securitySelf-learning systems for cyber security
Self-learning systems for cyber security
 
“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...
“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...
“Practical Guide to Implementing Deep Neural Network Inferencing at the Edge,...
 
Universal Adversarial Perturbation
Universal Adversarial PerturbationUniversal Adversarial Perturbation
Universal Adversarial Perturbation
 
Using classifiers to compute similarities between face images. Prof. Lior Wol...
Using classifiers to compute similarities between face images. Prof. Lior Wol...Using classifiers to compute similarities between face images. Prof. Lior Wol...
Using classifiers to compute similarities between face images. Prof. Lior Wol...
 
Strata San Jose 2016 - Reduce False Positives in Security
Strata San Jose 2016 - Reduce False Positives in Security Strata San Jose 2016 - Reduce False Positives in Security
Strata San Jose 2016 - Reduce False Positives in Security
 

Viewers also liked

Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Pluribus One
 
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Pluribus One
 
Understanding the risk factors of learning in adversarial environments
Understanding the risk factors of learning in adversarial environmentsUnderstanding the risk factors of learning in adversarial environments
Understanding the risk factors of learning in adversarial environments
Pluribus One
 
Causative Adversarial Learning
Causative Adversarial LearningCausative Adversarial Learning
Causative Adversarial Learning
David Dao
 
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Pluribus One
 
Making neural programming architectures generalize via recursion
Making neural programming architectures generalize via recursionMaking neural programming architectures generalize via recursion
Making neural programming architectures generalize via recursion
Katy Lee
 
What Makes Great Infographics
What Makes Great InfographicsWhat Makes Great Infographics
What Makes Great Infographics
SlideShare
 
Masters of SlideShare
Masters of SlideShareMasters of SlideShare
Masters of SlideShare
Kapost
 
STOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
STOP! VIEW THIS! 10-Step Checklist When Uploading to SlideshareSTOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
STOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
Empowered Presentations
 
You Suck At PowerPoint!
You Suck At PowerPoint!You Suck At PowerPoint!
You Suck At PowerPoint!
Jesse Desjardins - @jessedee
 
10 Ways to Win at SlideShare SEO & Presentation Optimization
10 Ways to Win at SlideShare SEO & Presentation Optimization10 Ways to Win at SlideShare SEO & Presentation Optimization
10 Ways to Win at SlideShare SEO & Presentation Optimization
Oneupweb
 
How To Get More From SlideShare - Super-Simple Tips For Content Marketing
How To Get More From SlideShare - Super-Simple Tips For Content MarketingHow To Get More From SlideShare - Super-Simple Tips For Content Marketing
How To Get More From SlideShare - Super-Simple Tips For Content Marketing
Content Marketing Institute
 
How to Make Awesome SlideShares: Tips & Tricks
How to Make Awesome SlideShares: Tips & TricksHow to Make Awesome SlideShares: Tips & Tricks
How to Make Awesome SlideShares: Tips & Tricks
SlideShare
 

Viewers also liked (13)

Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
Support Vector Machines Under Adversarial Label Noise (ACML 2011) - Battista ...
 
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
Battista Biggio @ ICML2012: "Poisoning attacks against support vector machines"
 
Understanding the risk factors of learning in adversarial environments
Understanding the risk factors of learning in adversarial environmentsUnderstanding the risk factors of learning in adversarial environments
Understanding the risk factors of learning in adversarial environments
 
Causative Adversarial Learning
Causative Adversarial LearningCausative Adversarial Learning
Causative Adversarial Learning
 
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Ph...
 
Making neural programming architectures generalize via recursion
Making neural programming architectures generalize via recursionMaking neural programming architectures generalize via recursion
Making neural programming architectures generalize via recursion
 
What Makes Great Infographics
What Makes Great InfographicsWhat Makes Great Infographics
What Makes Great Infographics
 
Masters of SlideShare
Masters of SlideShareMasters of SlideShare
Masters of SlideShare
 
STOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
STOP! VIEW THIS! 10-Step Checklist When Uploading to SlideshareSTOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
STOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
 
You Suck At PowerPoint!
You Suck At PowerPoint!You Suck At PowerPoint!
You Suck At PowerPoint!
 
10 Ways to Win at SlideShare SEO & Presentation Optimization
10 Ways to Win at SlideShare SEO & Presentation Optimization10 Ways to Win at SlideShare SEO & Presentation Optimization
10 Ways to Win at SlideShare SEO & Presentation Optimization
 
How To Get More From SlideShare - Super-Simple Tips For Content Marketing
How To Get More From SlideShare - Super-Simple Tips For Content MarketingHow To Get More From SlideShare - Super-Simple Tips For Content Marketing
How To Get More From SlideShare - Super-Simple Tips For Content Marketing
 
How to Make Awesome SlideShares: Tips & Tricks
How to Make Awesome SlideShares: Tips & TricksHow to Make Awesome SlideShares: Tips & Tricks
How to Make Awesome SlideShares: Tips & Tricks
 

Similar to Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning at test time

Lattice based Merkle for post-quantum epoch
Lattice based Merkle for post-quantum epochLattice based Merkle for post-quantum epoch
Lattice based Merkle for post-quantum epoch
DefCamp
 
isabelle_webinar_jan..
isabelle_webinar_jan..isabelle_webinar_jan..
isabelle_webinar_jan..
butest
 
Introduction
IntroductionIntroduction
Introduction
butest
 
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Universitat Politècnica de Catalunya
 
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
StampedeCon
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
Oswald Campesato
 
Scalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNetScalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNet
Amazon Web Services
 
Introduction to conventional machine learning techniques
Introduction to conventional machine learning techniquesIntroduction to conventional machine learning techniques
Introduction to conventional machine learning techniques
Xavier Rafael Palou
 
Introduction
IntroductionIntroduction
Introduction
butest
 
PPT
PPTPPT
PPT
butest
 
Multiple Classifier Systems for Adversarial Classification Tasks
Multiple Classifier Systems for Adversarial  Classification TasksMultiple Classifier Systems for Adversarial  Classification Tasks
Multiple Classifier Systems for Adversarial Classification Tasks
Pluribus One
 
Safety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfSafety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdf
Polytechnique Montréal
 
Introduction to Deep Learning and Tensorflow
Introduction to Deep Learning and TensorflowIntroduction to Deep Learning and Tensorflow
Introduction to Deep Learning and Tensorflow
Oswald Campesato
 
Deep Learning and TensorFlow
Deep Learning and TensorFlowDeep Learning and TensorFlow
Deep Learning and TensorFlow
Oswald Campesato
 
Two methods for optimising cognitive model parameters
Two methods for optimising cognitive model parametersTwo methods for optimising cognitive model parameters
Two methods for optimising cognitive model parameters
University of Huddersfield
 
1st review android malware.pptx
1st review  android malware.pptx1st review  android malware.pptx
1st review android malware.pptx
Nambiraju
 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_finance
Stefan Duprey
 
OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...
OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...
OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...
NETWAYS
 
ECCV2010: feature learning for image classification, part 4
ECCV2010: feature learning for image classification, part 4ECCV2010: feature learning for image classification, part 4
ECCV2010: feature learning for image classification, part 4
zukun
 
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Universitat Politècnica de Catalunya
 

Similar to Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning at test time (20)

Lattice based Merkle for post-quantum epoch
Lattice based Merkle for post-quantum epochLattice based Merkle for post-quantum epoch
Lattice based Merkle for post-quantum epoch
 
isabelle_webinar_jan..
isabelle_webinar_jan..isabelle_webinar_jan..
isabelle_webinar_jan..
 
Introduction
IntroductionIntroduction
Introduction
 
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
 
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Scalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNetScalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNet
 
Introduction to conventional machine learning techniques
Introduction to conventional machine learning techniquesIntroduction to conventional machine learning techniques
Introduction to conventional machine learning techniques
 
Introduction
IntroductionIntroduction
Introduction
 
PPT
PPTPPT
PPT
 
Multiple Classifier Systems for Adversarial Classification Tasks
Multiple Classifier Systems for Adversarial  Classification TasksMultiple Classifier Systems for Adversarial  Classification Tasks
Multiple Classifier Systems for Adversarial Classification Tasks
 
Safety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdfSafety Verification of Deep Neural Networks_.pdf
Safety Verification of Deep Neural Networks_.pdf
 
Introduction to Deep Learning and Tensorflow
Introduction to Deep Learning and TensorflowIntroduction to Deep Learning and Tensorflow
Introduction to Deep Learning and Tensorflow
 
Deep Learning and TensorFlow
Deep Learning and TensorFlowDeep Learning and TensorFlow
Deep Learning and TensorFlow
 
Two methods for optimising cognitive model parameters
Two methods for optimising cognitive model parametersTwo methods for optimising cognitive model parameters
Two methods for optimising cognitive model parameters
 
1st review android malware.pptx
1st review  android malware.pptx1st review  android malware.pptx
1st review android malware.pptx
 
Machine learning for_finance
Machine learning for_financeMachine learning for_finance
Machine learning for_finance
 
OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...
OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...
OSMC 2009 | Anomalieerkennung und Trendvorhersagen an Hand von Daten aus Nagi...
 
ECCV2010: feature learning for image classification, part 4
ECCV2010: feature learning for image classification, part 4ECCV2010: feature learning for image classification, part 4
ECCV2010: feature learning for image classification, part 4
 
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
Optimization (DLAI D4L1 2017 UPC Deep Learning for Artificial Intelligence)
 

More from Pluribus One

Smart Textiles - Prospettive di mercato - Davide Ariu
Smart Textiles - Prospettive di mercato - Davide Ariu Smart Textiles - Prospettive di mercato - Davide Ariu
Smart Textiles - Prospettive di mercato - Davide Ariu
Pluribus One
 
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...
Pluribus One
 
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Pluribus One
 
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Pluribus One
 
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
Pluribus One
 
Zahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense SlidesZahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense Slides
Pluribus One
 
Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...
Pluribus One
 
Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...
Pluribus One
 
Amilab IJCB 2011 Poster
Amilab IJCB 2011 PosterAmilab IJCB 2011 Poster
Amilab IJCB 2011 Poster
Pluribus One
 
Ariu - Workshop on Artificial Intelligence and Security - 2011
Ariu - Workshop on Artificial Intelligence and Security - 2011Ariu - Workshop on Artificial Intelligence and Security - 2011
Ariu - Workshop on Artificial Intelligence and Security - 2011
Pluribus One
 
Ariu - Workshop on Applications of Pattern Analysis 2010 - Poster
Ariu - Workshop on Applications of Pattern Analysis 2010 - PosterAriu - Workshop on Applications of Pattern Analysis 2010 - Poster
Ariu - Workshop on Applications of Pattern Analysis 2010 - Poster
Pluribus One
 
Ariu - Workshop on Multiple Classifier Systems - 2011
Ariu - Workshop on Multiple Classifier Systems - 2011Ariu - Workshop on Multiple Classifier Systems - 2011
Ariu - Workshop on Multiple Classifier Systems - 2011
Pluribus One
 
Ariu - Workshop on Applications of Pattern Analysis
Ariu - Workshop on Applications of Pattern AnalysisAriu - Workshop on Applications of Pattern Analysis
Ariu - Workshop on Applications of Pattern Analysis
Pluribus One
 
Ariu - Workshop on Multiple Classifier Systems 2011
Ariu - Workshop on Multiple Classifier Systems 2011Ariu - Workshop on Multiple Classifier Systems 2011
Ariu - Workshop on Multiple Classifier Systems 2011
Pluribus One
 
Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...
Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...
Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...
Pluribus One
 
Wiamis2010 poster
Wiamis2010 posterWiamis2010 poster
Wiamis2010 poster
Pluribus One
 

More from Pluribus One (16)

Smart Textiles - Prospettive di mercato - Davide Ariu
Smart Textiles - Prospettive di mercato - Davide Ariu Smart Textiles - Prospettive di mercato - Davide Ariu
Smart Textiles - Prospettive di mercato - Davide Ariu
 
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning - 2019 Int...
 
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
Wild Patterns: A Half-day Tutorial on Adversarial Machine Learning. ICMLC 201...
 
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
Wild patterns - Ten years after the rise of Adversarial Machine Learning - Ne...
 
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
WILD PATTERNS - Introduction to Adversarial Machine Learning - ITASEC 2019
 
Zahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense SlidesZahid Akhtar - Ph.D. Defense Slides
Zahid Akhtar - Ph.D. Defense Slides
 
Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...Design of robust classifiers for adversarial environments - Systems, Man, and...
Design of robust classifiers for adversarial environments - Systems, Man, and...
 
Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...Robustness of multimodal biometric verification systems under realistic spoof...
Robustness of multimodal biometric verification systems under realistic spoof...
 
Amilab IJCB 2011 Poster
Amilab IJCB 2011 PosterAmilab IJCB 2011 Poster
Amilab IJCB 2011 Poster
 
Ariu - Workshop on Artificial Intelligence and Security - 2011
Ariu - Workshop on Artificial Intelligence and Security - 2011Ariu - Workshop on Artificial Intelligence and Security - 2011
Ariu - Workshop on Artificial Intelligence and Security - 2011
 
Ariu - Workshop on Applications of Pattern Analysis 2010 - Poster
Ariu - Workshop on Applications of Pattern Analysis 2010 - PosterAriu - Workshop on Applications of Pattern Analysis 2010 - Poster
Ariu - Workshop on Applications of Pattern Analysis 2010 - Poster
 
Ariu - Workshop on Multiple Classifier Systems - 2011
Ariu - Workshop on Multiple Classifier Systems - 2011Ariu - Workshop on Multiple Classifier Systems - 2011
Ariu - Workshop on Multiple Classifier Systems - 2011
 
Ariu - Workshop on Applications of Pattern Analysis
Ariu - Workshop on Applications of Pattern AnalysisAriu - Workshop on Applications of Pattern Analysis
Ariu - Workshop on Applications of Pattern Analysis
 
Ariu - Workshop on Multiple Classifier Systems 2011
Ariu - Workshop on Multiple Classifier Systems 2011Ariu - Workshop on Multiple Classifier Systems 2011
Ariu - Workshop on Multiple Classifier Systems 2011
 
Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...
Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...
Robustness of Multimodal Biometric Systems under Realistic Spoof Attacks agai...
 
Wiamis2010 poster
Wiamis2010 posterWiamis2010 poster
Wiamis2010 poster
 

Recently uploaded

South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)
Academy of Science of South Africa
 
How to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRMHow to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRM
Celine George
 
writing about opinions about Australia the movie
writing about opinions about Australia the moviewriting about opinions about Australia the movie
writing about opinions about Australia the movie
Nicholas Montgomery
 
Film vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movieFilm vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movie
Nicholas Montgomery
 
C1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptx
C1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptxC1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptx
C1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptx
mulvey2
 
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat  Leveraging AI for Diversity, Equity, and InclusionExecutive Directors Chat  Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
TechSoup
 
How to Add Chatter in the odoo 17 ERP Module
How to Add Chatter in the odoo 17 ERP ModuleHow to Add Chatter in the odoo 17 ERP Module
How to Add Chatter in the odoo 17 ERP Module
Celine George
 
The simplified electron and muon model, Oscillating Spacetime: The Foundation...
The simplified electron and muon model, Oscillating Spacetime: The Foundation...The simplified electron and muon model, Oscillating Spacetime: The Foundation...
The simplified electron and muon model, Oscillating Spacetime: The Foundation...
RitikBhardwaj56
 
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama UniversityNatural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Akanksha trivedi rama nursing college kanpur.
 
How to Build a Module in Odoo 17 Using the Scaffold Method
How to Build a Module in Odoo 17 Using the Scaffold MethodHow to Build a Module in Odoo 17 Using the Scaffold Method
How to Build a Module in Odoo 17 Using the Scaffold Method
Celine George
 
Top five deadliest dog breeds in America
Top five deadliest dog breeds in AmericaTop five deadliest dog breeds in America
Top five deadliest dog breeds in America
Bisnar Chase Personal Injury Attorneys
 
The History of Stoke Newington Street Names
The History of Stoke Newington Street NamesThe History of Stoke Newington Street Names
The History of Stoke Newington Street Names
History of Stoke Newington
 
Hindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdfHindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdf
Dr. Mulla Adam Ali
 
PCOS corelations and management through Ayurveda.
PCOS corelations and management through Ayurveda.PCOS corelations and management through Ayurveda.
PCOS corelations and management through Ayurveda.
Dr. Shivangi Singh Parihar
 
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective UpskillingYour Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Excellence Foundation for South Sudan
 
Life upper-Intermediate B2 Workbook for student
Life upper-Intermediate B2 Workbook for studentLife upper-Intermediate B2 Workbook for student
Life upper-Intermediate B2 Workbook for student
NgcHiNguyn25
 
Main Java[All of the Base Concepts}.docx
Main Java[All of the Base Concepts}.docxMain Java[All of the Base Concepts}.docx
Main Java[All of the Base Concepts}.docx
adhitya5119
 
Introduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp NetworkIntroduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp Network
TechSoup
 
ANATOMY AND BIOMECHANICS OF HIP JOINT.pdf
ANATOMY AND BIOMECHANICS OF HIP JOINT.pdfANATOMY AND BIOMECHANICS OF HIP JOINT.pdf
ANATOMY AND BIOMECHANICS OF HIP JOINT.pdf
Priyankaranawat4
 
The Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collectionThe Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collection
Israel Genealogy Research Association
 

Recently uploaded (20)

South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)South African Journal of Science: Writing with integrity workshop (2024)
South African Journal of Science: Writing with integrity workshop (2024)
 
How to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRMHow to Manage Your Lost Opportunities in Odoo 17 CRM
How to Manage Your Lost Opportunities in Odoo 17 CRM
 
writing about opinions about Australia the movie
writing about opinions about Australia the moviewriting about opinions about Australia the movie
writing about opinions about Australia the movie
 
Film vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movieFilm vocab for eal 3 students: Australia the movie
Film vocab for eal 3 students: Australia the movie
 
C1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptx
C1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptxC1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptx
C1 Rubenstein AP HuG xxxxxxxxxxxxxx.pptx
 
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat  Leveraging AI for Diversity, Equity, and InclusionExecutive Directors Chat  Leveraging AI for Diversity, Equity, and Inclusion
Executive Directors Chat Leveraging AI for Diversity, Equity, and Inclusion
 
How to Add Chatter in the odoo 17 ERP Module
How to Add Chatter in the odoo 17 ERP ModuleHow to Add Chatter in the odoo 17 ERP Module
How to Add Chatter in the odoo 17 ERP Module
 
The simplified electron and muon model, Oscillating Spacetime: The Foundation...
The simplified electron and muon model, Oscillating Spacetime: The Foundation...The simplified electron and muon model, Oscillating Spacetime: The Foundation...
The simplified electron and muon model, Oscillating Spacetime: The Foundation...
 
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama UniversityNatural birth techniques - Mrs.Akanksha Trivedi Rama University
Natural birth techniques - Mrs.Akanksha Trivedi Rama University
 
How to Build a Module in Odoo 17 Using the Scaffold Method
How to Build a Module in Odoo 17 Using the Scaffold MethodHow to Build a Module in Odoo 17 Using the Scaffold Method
How to Build a Module in Odoo 17 Using the Scaffold Method
 
Top five deadliest dog breeds in America
Top five deadliest dog breeds in AmericaTop five deadliest dog breeds in America
Top five deadliest dog breeds in America
 
The History of Stoke Newington Street Names
The History of Stoke Newington Street NamesThe History of Stoke Newington Street Names
The History of Stoke Newington Street Names
 
Hindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdfHindi varnamala | hindi alphabet PPT.pdf
Hindi varnamala | hindi alphabet PPT.pdf
 
PCOS corelations and management through Ayurveda.
PCOS corelations and management through Ayurveda.PCOS corelations and management through Ayurveda.
PCOS corelations and management through Ayurveda.
 
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective UpskillingYour Skill Boost Masterclass: Strategies for Effective Upskilling
Your Skill Boost Masterclass: Strategies for Effective Upskilling
 
Life upper-Intermediate B2 Workbook for student
Life upper-Intermediate B2 Workbook for studentLife upper-Intermediate B2 Workbook for student
Life upper-Intermediate B2 Workbook for student
 
Main Java[All of the Base Concepts}.docx
Main Java[All of the Base Concepts}.docxMain Java[All of the Base Concepts}.docx
Main Java[All of the Base Concepts}.docx
 
Introduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp NetworkIntroduction to AI for Nonprofits with Tapp Network
Introduction to AI for Nonprofits with Tapp Network
 
ANATOMY AND BIOMECHANICS OF HIP JOINT.pdf
ANATOMY AND BIOMECHANICS OF HIP JOINT.pdfANATOMY AND BIOMECHANICS OF HIP JOINT.pdf
ANATOMY AND BIOMECHANICS OF HIP JOINT.pdf
 
The Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collectionThe Diamonds of 2023-2024 in the IGRA collection
The Diamonds of 2023-2024 in the IGRA collection
 

Battista Biggio @ ECML PKDD 2013 - Evasion attacks against machine learning at test time

  • 1. Pattern Recognition and Applications Lab                                   University of Cagliari, Italy   Department of Electrical and Electronic Engineering Evasion attacks against machine learning at test time Ba#sta  Biggio  (1)   Igino  Corona  (1),  Davide  Maiorca  (1),  Blaine  Nelson  (3),  Nedim  Šrndić  (2),   Pavel  Laskov  (2),  Giorgio  Giacinto  (1),  and  Fabio  Roli  (1)     (1)  University  of  Cagliari  (IT);  (2)  University  of  Tuebingen  (GE);  (3)  University  of  Postdam  (GE)  
  • 2.   http://pralab.diee.unica.it Machine learning in adversarial settings •  Machine learning in computer security –  spam filtering, intrusion detection, malware detection legitimate malicious x1   x2   f(x) 2  
  • 3.   http://pralab.diee.unica.it Machine learning in adversarial settings •  Machine learning in computer security –  spam filtering, intrusion detection, malware detection •  Adversaries manipulate samples at test time to evade detection legitimate malicious x1   x2   f(x) 3   Trading alert! We see a run starting to happen. It’s just beginning of 1 week promotion …Tr@ding al3rt! We see a run starting to happen. It’s just beginning of 1 week pr0m0ti0n …
  • 4.   http://pralab.diee.unica.it Our work Problem: can machine learning be secure? (1) •  Framework for proactive security evaluation of ML algorithms (2) Adversary model •  Goal of the attack •  Knowledge of the attacked system •  Capability of manipulating data •  Attack strategy as an optimization problem 4   Bounded adversary! (1)  M.  Barreno,  B.  Nelson,  R.  Sears,  A.  D.  Joseph,  and  J.  D.  Tygar.  Can   machine  learning  be  secure?  ASIACCS  2006   (2)  B.  Biggio,  G.  Fumera,  F.  Roli.  Security  evaluaVon  of  paWern  classifiers   under  aWack.  IEEE  Trans.  on  Knowl.  and  Data  Engineering,  2013   In  this  work  we  exploit  our  framework  for   security  evaluaVon  against  evasion  a)acks!  
  • 5.   http://pralab.diee.unica.it Bounding the adversary’s capability •  Cost of manipulations –  Spam: message readability •  Encoded by a distance function in feature space (L1-norm) –  e.g., number of words that are modified in spam emails 5   d (x, !x ) ≤ dmax x2   x1   f(x) Bounded by a maximum value x Feasible domain x ' We  will  evaluate  classifier   performance  vs.  increasing  dmax  
  • 6.   http://pralab.diee.unica.it Gradient-descent evasion attacks •  Goal: maximum-confidence evasion •  Knowledge: perfect •  Attack strategy: •  Non-linear, constrained optimization –  Gradient descent: approximate solution for smooth functions •  Gradients of g(x) can be analytically computed in many cases –  SVMs, Neural networks 6   −2−1.5−1−0.500.51 x f (x) = sign g(x)( )= +1, malicious −1, legitimate " # $ %$ min x' g(x') s.t. d(x, x') ≤ dmax x '
  • 7.   http://pralab.diee.unica.it Computing descent directions Support vector machines Neural networks 7   x1   xd   δ1   δk   δm   xf   g(x)   w1   wk   wm   v11   vmd   vk1   …… …… g(x) = αi yik(x, i ∑ xi )+ b, ∇g(x) = αi yi∇k(x, xi ) i ∑ g(x) = 1+exp − wkδk (x) k=1 m ∑ # $ % & ' ( ) * + , - . −1 ∂g(x) ∂xf = g(x) 1− g(x)( ) wkδk (x) 1−δk (x)( )vkf k=1 m ∑ RBF kernel gradient: ∇k (x,xi ) = −2γ exp −γ || x − xi ||2 { }(x − xi )
  • 8.   http://pralab.diee.unica.it g(x) − λ p(x|yc=−1), λ=0 −4 −3 −2 −1 0 1 2 3 4 −4 −2 0 2 4 −1 −0.5 0 0.5 1 •  Problem: greedily min. g(x) may not lead to classifier evasion! •  Solution: adding a mimicry component that attracts the attack samples towards samples classified as legitimate Density-augmented gradient-descent Mimicry component (Kernel Density Estimator) 8   g(x) − λ p(x|yc=−1), λ=20 −4 −3 −2 −1 0 1 2 3 4 −4 −2 0 2 4 −4.5 −4 −3.5 −3 −2.5 −2 −1.5 −1 Now  all  the  aWack  samples  evade   the  classifier!   Some  aWack  samples  may  not  evade   the  classifier!     min x' g(x')− λp(x' | yc = −1) s.t. d(x, x') ≤ dmax
  • 9.   http://pralab.diee.unica.it Density-augmented gradient-descent 9   ∇p(x | yc = −1) = − 2 nh exp − || x − xi ||2 h # $ % & ' ( x − xi( )i|yi c=−1∑KDE  gradient  (RBF  kernel):  
  • 10.   http://pralab.diee.unica.it An example on MNIST handwritten digits 10   •  Linear SVM, 3 vs 7. Features: pixel values. Before attack (3 vs 7) 5 10 15 20 25 5 10 15 20 25 After attack, g(x)=0 5 10 15 20 25 5 10 15 20 25 After attack, last iter. 5 10 15 20 25 5 10 15 20 25 0 500 −2 −1 0 1 2 g(x) number of iterations Without mimicry λ = 0 dmax 5000 Before attack (3 vs 7) 5 10 15 20 25 5 10 15 20 25 After attack, g(x)=0 5 10 15 20 25 5 10 15 20 25 After attack, last iter. 5 10 15 20 25 5 10 15 20 25 0 500 −2 −1 0 1 2 g(x) number of iterations With mimicry λ = 10 dmax 5000
  • 11.   http://pralab.diee.unica.it Bounding the adversary’s knowledge Limited knowledge attacks •  Only feature representation and learning algorithm are known •  Surrogate data sampled from the same distribution as the classifier’s training data •  Classifier’s feedback to label surrogate data 11   PD(X,Y)data   Surrogate training data f(x) Send queries Get labels Learn surrogate classifier f’(x)
  • 12.   http://pralab.diee.unica.it Experiments on PDF malware detection •  PDF: hierarchy of interconnected objects (keyword/value pairs) •  Adversary’s capability –  adding up to dmax objects to the PDF –  removing objects may compromise the PDF file (and embedded malware code)! 12   /Type    2   /Page    1   /Encoding  1   …   13  0  obj   <<  /Kids  [  1  0  R  11  0  R  ]   /Type  /Page   ...  >>  end  obj   17  0  obj   <<  /Type  /Encoding   /Differences  [  0  /C0032  ]  >>   endobj     Features:  keyword  count   min x' g(x')− λp(x' | y = −1) s.t. d(x, x') ≤ dmax x ≤ x'
  • 13.   http://pralab.diee.unica.it 0 10 20 30 40 50 0 0.2 0.4 0.6 0.8 1 dmax FN SVM (Linear), λ=0 PK (C=1) LK (C=1) Experiments on PDF malware detection Linear SVM 13   0 10 20 30 40 50 0 0.2 0.4 0.6 0.8 1 SVM (linear) − C=1, λ=500 dmax FN PK LK •  Dataset: 500 malware samples (Contagio), 500 benign (Internet) –  5-fold cross-validation –  Targeted (surrogate) classifier trained on 500 (100) samples •  Evasion rate (FN) at FP=1% vs max. number of added keywords –  Perfect knowledge (PK); Limited knowledge (LK) Without mimicry λ = 0 With mimicry λ = 500
  • 14.   http://pralab.diee.unica.it Experiments on PDF malware detection SVM with RBF kernel, Neural Network 14   0 10 20 30 40 50 0 0.2 0.4 0.6 0.8 1 Neural Netw. − m=5,λ=500 dmax FN PK LK 0 10 20 30 40 50 0 0.2 0.4 0.6 0.8 1 SVM (RBF) − C=1, γ=1, λ=500 dmax FN PK LK 0 10 20 30 40 50 0 0.2 0.4 0.6 0.8 1 dmax FN SVM (RBF), λ=0 PK (C=1) LK (C=1) 0 10 20 30 40 50 0 0.2 0.4 0.6 0.8 1 dmax FN Neural Netw., λ=0 PK (C=1) LK (C=1) (m=5) (m=5)
  • 15.   http://pralab.diee.unica.it Conclusions and future work •  Related work. Near-optimal evasion of linear and convex- inducing classifiers (1,2) •  Our work. Linear and non-linear classifiers can be highly vulnerable to well-crafted evasion attacks –  … even under limited attacker’s knowledge •  Future work –  Evasion of non-differentiable decision functions (decision trees) –  Surrogate data: how to query more efficiently the targeted classifier? –  Practical evasion: feature representation partially known or difficult to reverse-engineer –  Securing learning: game theory to model classifier vs. adversary 15   (1)  D.  Lowd  and  C.  Meek.  Adversarial  learning.  ACM  SIGKDD,  2005.   (2)  B.  Nelson,  B.  I.  Rubinstein,  L.  Huang,  A.  D.  Joseph,  S.  J.  Lee,  S.  Rao,  and  J.  D.   Tygar.  Query  strategies  for  evading  convex-­‐inducing  classifiers.  JMLR,  2012.  
  • 16.   http://pralab.diee.unica.it ?   16     Any  ques@ons  Thanks  for  your  aWenVon!