SlideShare a Scribd company logo
1 of 18
Download to read offline
Oblivious Neural Network
Predictions via MiniONN
Transformations
Presented by: Sherif Abdelfattah
Liu, J., Juuti, M., Lu, Y., & Asokan, N. (2017, October). Oblivious neural network predictions via minionn
transformations. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications
Security (pp. 619-631). ACM. (121 citation)
1
Machine Learning as a Service
Input
Predictions
This way is a violation of clients’ privacy
2
Running predictions on client-side
• A naive solution is to have clients download the model and run the
prediction phase on client-side.
Model
• It becomes more difficult for service providers to update their models.
• For security applications (e.g., spam or malware detection services), an adversary can use
the model as an oracle to develop strategies for evading detection.
• If the training data contains sensitive information (such as patient records from a
hospital) revealing the model may compromise privacy of the training data.
3
Oblivious Neural Networks (ONN)
The solution is using make the neural network oblivious
• The server learns nothing about the client’s input.
• The clients learn nothing about the model.
4
MiniONN
Blinded Input
Blinded Predictions
Oblivious Protocols
• Low overhead almost 1 s
• Work with all neural networks
• MiniONN: Minimizing the Overhead for Oblivious Neural Network
6
How it works?
𝑋 =
𝑥1
𝑥2
, 𝑊 =
𝑤1,1 𝑤1,2
𝑤2,1 𝑤2,2
, 𝑏 =
𝑏1
𝑏2
, 𝑊′ =
𝑤′
1,1 𝑤′
1,2
𝑤′
2,1 𝑤′
2,2
, 𝑏′ =
𝑏′1
𝑏′2
𝑾′. 𝑿′ + 𝒃′
𝒇( 𝒚 )
𝑾. 𝑿 + 𝒃
𝑿
𝒚
𝑿’
𝒁
Represents Linear Transformation
Represents Non-Linear
Transformation (Activation Function)
𝒁 = 𝑾′. 𝒇 𝑾. 𝑿 + 𝒃 + 𝒃′
7
Core Idea
• The core idea is to use secret sharing for oblivious computation.
𝑾′. + 𝒃′
𝒇( )
𝑾. + 𝒃
𝒚𝒄
𝒙′𝒄
𝒙𝐜 𝒙𝐬
𝒚𝒔
𝒙′𝒔
Client
Server
𝒚′𝒄
𝒚′𝒔
𝒁
𝑥𝑐
+ 𝑥𝑠
= 𝑋
𝑦𝑐
+ 𝑦𝑠
= 𝑦
𝑥′𝑐 + 𝑥′𝑠 = 𝑋′
𝑦′𝑐
+ 𝑦′𝑠
= 𝑦′
The client & the server shares
𝑥𝑐
and 𝑥𝑠
8
Secret sharing input 𝑿
𝒙𝟏
𝒄
, 𝒙𝟐
𝒄
𝒓𝒂𝒏𝒅𝒐𝒎
𝒁𝑵
𝒙𝟏
𝒔
= 𝒙𝟏 − 𝒙𝟏
𝒄
𝒙𝟐
𝒔
= 𝒙𝟐 − 𝒙𝟐
𝒄
𝒙𝟏
𝒔
, 𝒙𝟐
𝒔
𝒙𝒄
is independent of 𝒙 so it
can be pre-chosen
9
Oblivious linear transformation 𝑾. 𝑿 + 𝒃
𝑤1,1 𝑤1,2
𝑤2,1 𝑤2,2
⋅
𝑥1
𝑥2
+
𝑏1
𝑏2
=
𝑤1,1 𝑤1,2
𝑤2,1 𝑤2,2
⋅
𝑥1
𝑠
+ 𝑥1
𝑐
𝑥2
𝑠
+𝑥2
𝑐 +
𝑏1
𝑏2
=
𝑤1,1(𝑥1
𝑠
+ 𝑥1
𝑐
) + 𝑤1,2 𝑥2
𝑠
+𝑥2
𝑐
+ 𝑏1
𝑤2,1(𝑥1
𝑠
+ 𝑥1
𝑐
) + 𝑤2,2 𝑥2
𝑠
+𝑥2
𝑐
+ 𝑏2
=
𝑤1,1𝑥1
𝑠
+ 𝑤1,2𝑥2
𝑠
+ 𝑏1 + 𝑤1,1𝑥1
𝑐
+𝑤1,2𝑥2
𝑐
𝑤2,1𝑥1
𝑠
+ 𝑤2,2𝑥2
𝑠
+ 𝑏2 + 𝑤2,1𝑥1
𝑐
+ 𝑤2,2𝑥2
𝑐
Compute locally by the server Dot-product
10
Oblivious linear transformation (dot-product)
𝑟1,1, 𝑟1,2, 𝑟2,1, 𝑟2,2
𝑟𝑎𝑛𝑑𝑜𝑚
𝑍𝑁 𝐸 𝑤1,1 , 𝐸 𝑤1,2 , 𝐸 𝑤2,1 , 𝐸 𝑤2,2
Homomorphic Encryption with SIMD1
1Single instruction multiple data (SIMD): technique used to reduce the memory of the circuit and improve the evaluation time.
𝑐1,1 = 𝐸 𝑤1,1𝑥1
𝑐
− 𝑟1,1
𝑐1,2 = 𝐸 𝑤1,2𝑥2
𝑐
− 𝑟1,2
𝑐2,1 = 𝐸 𝑤2,1𝑥1
𝑐
− 𝑟2,1
𝑐2,2 = 𝐸 𝑤2,2𝑥2
𝑐
− 𝑟2,2 𝑐1,1, 𝑐1,2, 𝑐2,1, 𝑐2,2
𝐷(𝑐1,1), 𝐷(𝑐1,2), 𝐷(𝑐2,1), 𝐷(𝑐2,2)
𝑢1 = 𝐷(𝑐1,1) + 𝐷(𝑐1,2) = 𝑤1,1𝑥1
𝑐
+ 𝑤1,2𝑥2
𝑐
− (𝑟1,1+𝑟1,2)
𝑢2 = 𝐷(𝑐2,1) + 𝐷(𝑐2,2) = 𝑤2,1𝑥1
𝑐
+ 𝑤2,2𝑥2
𝑐
− (𝑟2,1+𝑟2,2)
𝑣1 = 𝑟1,1 + 𝑟1,2
𝑣2 = 𝑟2,1 + 𝑟2,2
11
Oblivious linear transformation 𝑾. 𝑿 + 𝒃
=
𝑤1,1𝑥1
𝑠
+ 𝑤1,2𝑥2
𝑠
+ 𝑏1 + 𝑤1,1𝑥1
𝑐
+𝑤1,2𝑥2
𝑐
𝑤2,1𝑥1
𝑠
+ 𝑤2,2𝑥2
𝑠
+ 𝑏2 + 𝑤2,1𝑥1
𝑐
+ 𝑤2,2𝑥2
𝑐
=
𝑤1,1𝑥1
𝑠
+ 𝑤1,2𝑥2
𝑠
+ 𝑏1 + 𝑢1
𝑤2,1𝑥1
𝑠
+ 𝑤2,2𝑥2
𝑠
+ 𝑏2 + 𝑢2
+
𝑣1
𝑣2
=
𝑦1
𝑠
𝑦2
𝑠 +
𝑦1
𝑐
𝑦2
𝑐
12
Oblivious Activation Functions 𝒇(𝒚)
Piecewise linear functions
• For example (ReLU: 𝑥 = compare(𝑦, 0))
• Oblivious ReLU 𝑥𝑠+𝑥𝑐= compare 𝑦𝑠 + 𝑦𝑐, 0
• Computed obliviously by a garbled circuit2
2garbled circuit: is a two-party computation (2PC) technique that allow two parties to jointly compute a function without learning each other’s input.
13
Oblivious Activation Functions 𝒇(𝒚)
Smooth functions
• For example (Sigmoid: 𝑥 = Τ
1 1 + 𝑒−𝑦 )
• Oblivious Sigmoid 𝑥𝑠+𝑥𝑐= Τ
1 1 + 𝑒−(𝑦𝑠+𝑦𝑐)
• Approximate by a piecewise linear function
• Computed obliviously by a garbled circuit
14
The final result
𝑦1
𝑠
, 𝑦2
𝑠
𝑦1 = 𝑦1
𝑐
+ 𝑦1
𝑠
𝑦2 = 𝑦2
𝑐
+ 𝑦2
𝑠
15
Performance
1. MNIST (60 000 training images and 10 000 test images)
• Handwriting recognition
• CNN model
• ReLU activation function
2. CIFAR-10 (50 000 training images and 10 000 test images)
• Image classification
• CNN model
• ReLU activation function
3. Penn Treebank (PTB) (929 000 training words, 73 000 validation words, and 82 000 test words.)
• language modeling: predicting next words given the previous words
• Long Short Term Memory (LSTM): commonly used for language modeling
• Sigmoidal activation function
16
Performance
MNIST/Square/CNN
Latency (s) Msg sizes (MB)
Accuracy %
offline online offline online
CryptoNets 0 297.5 0 372.2 98.95
MiniONN 0.88 0.4 3.6 44 98.95
• Comparison between MiniONN vs. CryptoNets
17
Performance
Model
Latency (s) Msg sizes (MB)
Accuracy %
offline online offline online
MNIST/ReLU/CNN 3.58 5.74 20.9 20.9 99.0
CIFAR-10/ReLU/CNN 472 72 3046 6226 81.61
PTB/Sigmoidal/LSTM 13.9 4.39 86.7 474
cross-entropy
loss:4.79
• For single query
18
Thank You
19

More Related Content

What's hot

Fundamentals of Data compression
Fundamentals of Data compressionFundamentals of Data compression
Fundamentals of Data compressionM.k. Praveen
 
Data compression
Data compressionData compression
Data compressionNizar Sbaih
 
Hufman coding basic
Hufman coding basicHufman coding basic
Hufman coding basicradthees
 
Image compression: Techniques and Application
Image compression: Techniques and ApplicationImage compression: Techniques and Application
Image compression: Techniques and ApplicationNidhi Baranwal
 
data compression technique
data compression techniquedata compression technique
data compression techniqueCHINMOY PAUL
 
Data compression & Classification
Data compression & ClassificationData compression & Classification
Data compression & ClassificationKhulna University
 
Interpixel redundancy
Interpixel redundancyInterpixel redundancy
Interpixel redundancyNaveen Kumar
 
Image compression
Image compressionImage compression
Image compressionHuda Seyam
 
Data compression techniques
Data compression techniquesData compression techniques
Data compression techniquesDeep Bhatt
 
image compresson
image compressonimage compresson
image compressonAjay Kumar
 
Compression using JPEG
Compression using JPEGCompression using JPEG
Compression using JPEGSabih Hasan
 
Why Image compression is Necessary?
Why Image compression is Necessary?Why Image compression is Necessary?
Why Image compression is Necessary?Prabhat Kumar
 

What's hot (20)

Image compression
Image compressionImage compression
Image compression
 
Fundamentals of Data compression
Fundamentals of Data compressionFundamentals of Data compression
Fundamentals of Data compression
 
Data compression
Data compressionData compression
Data compression
 
Hufman coding basic
Hufman coding basicHufman coding basic
Hufman coding basic
 
Image compression: Techniques and Application
Image compression: Techniques and ApplicationImage compression: Techniques and Application
Image compression: Techniques and Application
 
data compression technique
data compression techniquedata compression technique
data compression technique
 
Image compression and jpeg
Image compression and jpegImage compression and jpeg
Image compression and jpeg
 
Data Redundacy
Data RedundacyData Redundacy
Data Redundacy
 
Data compression & Classification
Data compression & ClassificationData compression & Classification
Data compression & Classification
 
Interpixel redundancy
Interpixel redundancyInterpixel redundancy
Interpixel redundancy
 
Data compression
Data compressionData compression
Data compression
 
Introduction Data Compression/ Data compression, modelling and coding,Image C...
Introduction Data Compression/ Data compression, modelling and coding,Image C...Introduction Data Compression/ Data compression, modelling and coding,Image C...
Introduction Data Compression/ Data compression, modelling and coding,Image C...
 
Image compression
Image compressionImage compression
Image compression
 
Data compression techniques
Data compression techniquesData compression techniques
Data compression techniques
 
image compresson
image compressonimage compresson
image compresson
 
Run length encoding
Run length encodingRun length encoding
Run length encoding
 
Image Compression, Introduction Data Compression/ Data compression, modelling...
Image Compression, Introduction Data Compression/ Data compression, modelling...Image Compression, Introduction Data Compression/ Data compression, modelling...
Image Compression, Introduction Data Compression/ Data compression, modelling...
 
Compression using JPEG
Compression using JPEGCompression using JPEG
Compression using JPEG
 
Why Image compression is Necessary?
Why Image compression is Necessary?Why Image compression is Necessary?
Why Image compression is Necessary?
 
Image compression
Image compression Image compression
Image compression
 

Similar to Oblivious Neural Network Predictions via MiniONN Transformations

Machine Learning Essentials Demystified part2 | Big Data Demystified
Machine Learning Essentials Demystified part2 | Big Data DemystifiedMachine Learning Essentials Demystified part2 | Big Data Demystified
Machine Learning Essentials Demystified part2 | Big Data DemystifiedOmid Vahdaty
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionTe-Yen Liu
 
Deep learning from scratch
Deep learning from scratch Deep learning from scratch
Deep learning from scratch Eran Shlomo
 
08 neural networks
08 neural networks08 neural networks
08 neural networksankit_ppt
 
Thesis Presentation on Energy Efficiency Improvement in Data Centers
Thesis Presentation on Energy Efficiency Improvement in Data CentersThesis Presentation on Energy Efficiency Improvement in Data Centers
Thesis Presentation on Energy Efficiency Improvement in Data CentersMonica Vitali
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System OperationsIRJET Journal
 
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...Ryo Takahashi
 
deep learning from scratch chapter 3 neural network
deep learning from scratch chapter 3 neural networkdeep learning from scratch chapter 3 neural network
deep learning from scratch chapter 3 neural networkJaey Jeong
 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural NetworksDatabricks
 
Deep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationDeep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationYan Xu
 
Monitoring Complex Systems: Keeping Your Head on Straight in a Hard World
Monitoring Complex Systems: Keeping Your Head on Straight in a Hard WorldMonitoring Complex Systems: Keeping Your Head on Straight in a Hard World
Monitoring Complex Systems: Keeping Your Head on Straight in a Hard WorldBrian Troutwine
 
Blood Cell Image Classification for Detecting Malaria using CNN
Blood Cell Image Classification for Detecting Malaria using CNNBlood Cell Image Classification for Detecting Malaria using CNN
Blood Cell Image Classification for Detecting Malaria using CNNIRJET Journal
 
FastV2C-HandNet - ICICC 2020
FastV2C-HandNet - ICICC 2020FastV2C-HandNet - ICICC 2020
FastV2C-HandNet - ICICC 2020RohanLekhwani
 
Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017Gabriel Moreira
 
Distributed Deep Learning Using Java on the Client and in the Cloud
Distributed Deep Learning Using Java on the Client and in the CloudDistributed Deep Learning Using Java on the Client and in the Cloud
Distributed Deep Learning Using Java on the Client and in the CloudData Science Leuven
 
Batch normalization presentation
Batch normalization presentationBatch normalization presentation
Batch normalization presentationOwin Will
 
Enhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithmEnhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithmHadi Fadlallah
 

Similar to Oblivious Neural Network Predictions via MiniONN Transformations (20)

Machine Learning Essentials Demystified part2 | Big Data Demystified
Machine Learning Essentials Demystified part2 | Big Data DemystifiedMachine Learning Essentials Demystified part2 | Big Data Demystified
Machine Learning Essentials Demystified part2 | Big Data Demystified
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis Introduction
 
Deep learning from scratch
Deep learning from scratch Deep learning from scratch
Deep learning from scratch
 
08 neural networks
08 neural networks08 neural networks
08 neural networks
 
Thesis Presentation on Energy Efficiency Improvement in Data Centers
Thesis Presentation on Energy Efficiency Improvement in Data CentersThesis Presentation on Energy Efficiency Improvement in Data Centers
Thesis Presentation on Energy Efficiency Improvement in Data Centers
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System Operations
 
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic...
 
deep learning from scratch chapter 3 neural network
deep learning from scratch chapter 3 neural networkdeep learning from scratch chapter 3 neural network
deep learning from scratch chapter 3 neural network
 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural Networks
 
Deep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationDeep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and Regularization
 
Neural networks
Neural networksNeural networks
Neural networks
 
Monitoring Complex Systems: Keeping Your Head on Straight in a Hard World
Monitoring Complex Systems: Keeping Your Head on Straight in a Hard WorldMonitoring Complex Systems: Keeping Your Head on Straight in a Hard World
Monitoring Complex Systems: Keeping Your Head on Straight in a Hard World
 
Session 4 .pdf
Session 4 .pdfSession 4 .pdf
Session 4 .pdf
 
Blood Cell Image Classification for Detecting Malaria using CNN
Blood Cell Image Classification for Detecting Malaria using CNNBlood Cell Image Classification for Detecting Malaria using CNN
Blood Cell Image Classification for Detecting Malaria using CNN
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
FastV2C-HandNet - ICICC 2020
FastV2C-HandNet - ICICC 2020FastV2C-HandNet - ICICC 2020
FastV2C-HandNet - ICICC 2020
 
Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017Feature Engineering - Getting most out of data for predictive models - TDC 2017
Feature Engineering - Getting most out of data for predictive models - TDC 2017
 
Distributed Deep Learning Using Java on the Client and in the Cloud
Distributed Deep Learning Using Java on the Client and in the CloudDistributed Deep Learning Using Java on the Client and in the Cloud
Distributed Deep Learning Using Java on the Client and in the Cloud
 
Batch normalization presentation
Batch normalization presentationBatch normalization presentation
Batch normalization presentation
 
Enhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithmEnhancing the performance of kmeans algorithm
Enhancing the performance of kmeans algorithm
 

Recently uploaded

Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)Suman Mia
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...srsj9000
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxAsutosh Ranjan
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxupamatechverse
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...ranjana rawat
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile servicerehmti665
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVRajaP95
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSCAESB
 
Analog to Digital and Digital to Analog Converter
Analog to Digital and Digital to Analog ConverterAnalog to Digital and Digital to Analog Converter
Analog to Digital and Digital to Analog ConverterAbhinavSharma374939
 

Recently uploaded (20)

Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
 
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
★ CALL US 9953330565 ( HOT Young Call Girls In Badarpur delhi NCR
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINEDJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
DJARUM4D - SLOT GACOR ONLINE | SLOT DEMO ONLINE
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile service
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentation
 
Analog to Digital and Digital to Analog Converter
Analog to Digital and Digital to Analog ConverterAnalog to Digital and Digital to Analog Converter
Analog to Digital and Digital to Analog Converter
 

Oblivious Neural Network Predictions via MiniONN Transformations

  • 1. Oblivious Neural Network Predictions via MiniONN Transformations Presented by: Sherif Abdelfattah Liu, J., Juuti, M., Lu, Y., & Asokan, N. (2017, October). Oblivious neural network predictions via minionn transformations. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (pp. 619-631). ACM. (121 citation) 1
  • 2. Machine Learning as a Service Input Predictions This way is a violation of clients’ privacy 2
  • 3. Running predictions on client-side • A naive solution is to have clients download the model and run the prediction phase on client-side. Model • It becomes more difficult for service providers to update their models. • For security applications (e.g., spam or malware detection services), an adversary can use the model as an oracle to develop strategies for evading detection. • If the training data contains sensitive information (such as patient records from a hospital) revealing the model may compromise privacy of the training data. 3
  • 4. Oblivious Neural Networks (ONN) The solution is using make the neural network oblivious • The server learns nothing about the client’s input. • The clients learn nothing about the model. 4
  • 5. MiniONN Blinded Input Blinded Predictions Oblivious Protocols • Low overhead almost 1 s • Work with all neural networks • MiniONN: Minimizing the Overhead for Oblivious Neural Network 6
  • 6. How it works? 𝑋 = 𝑥1 𝑥2 , 𝑊 = 𝑤1,1 𝑤1,2 𝑤2,1 𝑤2,2 , 𝑏 = 𝑏1 𝑏2 , 𝑊′ = 𝑤′ 1,1 𝑤′ 1,2 𝑤′ 2,1 𝑤′ 2,2 , 𝑏′ = 𝑏′1 𝑏′2 𝑾′. 𝑿′ + 𝒃′ 𝒇( 𝒚 ) 𝑾. 𝑿 + 𝒃 𝑿 𝒚 𝑿’ 𝒁 Represents Linear Transformation Represents Non-Linear Transformation (Activation Function) 𝒁 = 𝑾′. 𝒇 𝑾. 𝑿 + 𝒃 + 𝒃′ 7
  • 7. Core Idea • The core idea is to use secret sharing for oblivious computation. 𝑾′. + 𝒃′ 𝒇( ) 𝑾. + 𝒃 𝒚𝒄 𝒙′𝒄 𝒙𝐜 𝒙𝐬 𝒚𝒔 𝒙′𝒔 Client Server 𝒚′𝒄 𝒚′𝒔 𝒁 𝑥𝑐 + 𝑥𝑠 = 𝑋 𝑦𝑐 + 𝑦𝑠 = 𝑦 𝑥′𝑐 + 𝑥′𝑠 = 𝑋′ 𝑦′𝑐 + 𝑦′𝑠 = 𝑦′ The client & the server shares 𝑥𝑐 and 𝑥𝑠 8
  • 8. Secret sharing input 𝑿 𝒙𝟏 𝒄 , 𝒙𝟐 𝒄 𝒓𝒂𝒏𝒅𝒐𝒎 𝒁𝑵 𝒙𝟏 𝒔 = 𝒙𝟏 − 𝒙𝟏 𝒄 𝒙𝟐 𝒔 = 𝒙𝟐 − 𝒙𝟐 𝒄 𝒙𝟏 𝒔 , 𝒙𝟐 𝒔 𝒙𝒄 is independent of 𝒙 so it can be pre-chosen 9
  • 9. Oblivious linear transformation 𝑾. 𝑿 + 𝒃 𝑤1,1 𝑤1,2 𝑤2,1 𝑤2,2 ⋅ 𝑥1 𝑥2 + 𝑏1 𝑏2 = 𝑤1,1 𝑤1,2 𝑤2,1 𝑤2,2 ⋅ 𝑥1 𝑠 + 𝑥1 𝑐 𝑥2 𝑠 +𝑥2 𝑐 + 𝑏1 𝑏2 = 𝑤1,1(𝑥1 𝑠 + 𝑥1 𝑐 ) + 𝑤1,2 𝑥2 𝑠 +𝑥2 𝑐 + 𝑏1 𝑤2,1(𝑥1 𝑠 + 𝑥1 𝑐 ) + 𝑤2,2 𝑥2 𝑠 +𝑥2 𝑐 + 𝑏2 = 𝑤1,1𝑥1 𝑠 + 𝑤1,2𝑥2 𝑠 + 𝑏1 + 𝑤1,1𝑥1 𝑐 +𝑤1,2𝑥2 𝑐 𝑤2,1𝑥1 𝑠 + 𝑤2,2𝑥2 𝑠 + 𝑏2 + 𝑤2,1𝑥1 𝑐 + 𝑤2,2𝑥2 𝑐 Compute locally by the server Dot-product 10
  • 10. Oblivious linear transformation (dot-product) 𝑟1,1, 𝑟1,2, 𝑟2,1, 𝑟2,2 𝑟𝑎𝑛𝑑𝑜𝑚 𝑍𝑁 𝐸 𝑤1,1 , 𝐸 𝑤1,2 , 𝐸 𝑤2,1 , 𝐸 𝑤2,2 Homomorphic Encryption with SIMD1 1Single instruction multiple data (SIMD): technique used to reduce the memory of the circuit and improve the evaluation time. 𝑐1,1 = 𝐸 𝑤1,1𝑥1 𝑐 − 𝑟1,1 𝑐1,2 = 𝐸 𝑤1,2𝑥2 𝑐 − 𝑟1,2 𝑐2,1 = 𝐸 𝑤2,1𝑥1 𝑐 − 𝑟2,1 𝑐2,2 = 𝐸 𝑤2,2𝑥2 𝑐 − 𝑟2,2 𝑐1,1, 𝑐1,2, 𝑐2,1, 𝑐2,2 𝐷(𝑐1,1), 𝐷(𝑐1,2), 𝐷(𝑐2,1), 𝐷(𝑐2,2) 𝑢1 = 𝐷(𝑐1,1) + 𝐷(𝑐1,2) = 𝑤1,1𝑥1 𝑐 + 𝑤1,2𝑥2 𝑐 − (𝑟1,1+𝑟1,2) 𝑢2 = 𝐷(𝑐2,1) + 𝐷(𝑐2,2) = 𝑤2,1𝑥1 𝑐 + 𝑤2,2𝑥2 𝑐 − (𝑟2,1+𝑟2,2) 𝑣1 = 𝑟1,1 + 𝑟1,2 𝑣2 = 𝑟2,1 + 𝑟2,2 11
  • 11. Oblivious linear transformation 𝑾. 𝑿 + 𝒃 = 𝑤1,1𝑥1 𝑠 + 𝑤1,2𝑥2 𝑠 + 𝑏1 + 𝑤1,1𝑥1 𝑐 +𝑤1,2𝑥2 𝑐 𝑤2,1𝑥1 𝑠 + 𝑤2,2𝑥2 𝑠 + 𝑏2 + 𝑤2,1𝑥1 𝑐 + 𝑤2,2𝑥2 𝑐 = 𝑤1,1𝑥1 𝑠 + 𝑤1,2𝑥2 𝑠 + 𝑏1 + 𝑢1 𝑤2,1𝑥1 𝑠 + 𝑤2,2𝑥2 𝑠 + 𝑏2 + 𝑢2 + 𝑣1 𝑣2 = 𝑦1 𝑠 𝑦2 𝑠 + 𝑦1 𝑐 𝑦2 𝑐 12
  • 12. Oblivious Activation Functions 𝒇(𝒚) Piecewise linear functions • For example (ReLU: 𝑥 = compare(𝑦, 0)) • Oblivious ReLU 𝑥𝑠+𝑥𝑐= compare 𝑦𝑠 + 𝑦𝑐, 0 • Computed obliviously by a garbled circuit2 2garbled circuit: is a two-party computation (2PC) technique that allow two parties to jointly compute a function without learning each other’s input. 13
  • 13. Oblivious Activation Functions 𝒇(𝒚) Smooth functions • For example (Sigmoid: 𝑥 = Τ 1 1 + 𝑒−𝑦 ) • Oblivious Sigmoid 𝑥𝑠+𝑥𝑐= Τ 1 1 + 𝑒−(𝑦𝑠+𝑦𝑐) • Approximate by a piecewise linear function • Computed obliviously by a garbled circuit 14
  • 14. The final result 𝑦1 𝑠 , 𝑦2 𝑠 𝑦1 = 𝑦1 𝑐 + 𝑦1 𝑠 𝑦2 = 𝑦2 𝑐 + 𝑦2 𝑠 15
  • 15. Performance 1. MNIST (60 000 training images and 10 000 test images) • Handwriting recognition • CNN model • ReLU activation function 2. CIFAR-10 (50 000 training images and 10 000 test images) • Image classification • CNN model • ReLU activation function 3. Penn Treebank (PTB) (929 000 training words, 73 000 validation words, and 82 000 test words.) • language modeling: predicting next words given the previous words • Long Short Term Memory (LSTM): commonly used for language modeling • Sigmoidal activation function 16
  • 16. Performance MNIST/Square/CNN Latency (s) Msg sizes (MB) Accuracy % offline online offline online CryptoNets 0 297.5 0 372.2 98.95 MiniONN 0.88 0.4 3.6 44 98.95 • Comparison between MiniONN vs. CryptoNets 17
  • 17. Performance Model Latency (s) Msg sizes (MB) Accuracy % offline online offline online MNIST/ReLU/CNN 3.58 5.74 20.9 20.9 99.0 CIFAR-10/ReLU/CNN 472 72 3046 6226 81.61 PTB/Sigmoidal/LSTM 13.9 4.39 86.7 474 cross-entropy loss:4.79 • For single query 18