convolutional neural networks with data augmentation
play

Convolutional Neural Networks with Data Augmentation against - PowerPoint PPT Presentation

Oct 24, 2023 •258 likes •1.28k views

Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Eleonora Cagli 1 , 3 ecile Dumas 1 C Emmanuel Prouff 2 , 3 1

  1. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Eleonora Cagli 1 , 3 ecile Dumas 1 C´ Emmanuel Prouff 2 , 3 1 Univ. Grenoble Alpes, F-38000, Grenoble, France CEA, LETI, MINATEC Campus, F-38054 Grenoble, France { eleonora.cagli,cecile.dumas } @cea.fr 2 Safran Identity and Security, France emmanuel.prouff@safrangroup.com 3 Sorbonne Universit´ es, UPMC Univ. Paris 06, CNRS, INRIA, Laboratoire d’Informatique de Paris 6 (LIP6), ´ Equipe PolSys, 4 place Jussieu, 75252 Paris Cedex 05, France 26/09/2017, CHES 2017, Taipei, Taiwan 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 1/26

  2. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures About the authors Who we are Conceives a Evaluates Delivers a Security Commercialises the component Security Claims Certification certified product Developer ITSEF ANSSI Developer French Certification Scheme 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 2/26

  3. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures About the authors Who we are Conceives a Evaluates Delivers a Security Commercialises the component Security Claims Certification certified product Developer ITSEF ANSSI Developer French Certification Scheme Cécile 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 2/26

  4. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures About the authors Who we are Conceives a Evaluates Delivers a Security Commercialises the component Security Claims Certification certified product Developer ITSEF ANSSI Developer French Certification Scheme Cécile Eleonora 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 2/26

  5. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures About the authors Who we are Conceives a Evaluates Delivers a Security Commercialises the component Security Claims Certification certified product Developer ITSEF ANSSI Developer Emmanuel (in the past) French Certification Scheme Cécile Eleonora 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 2/26

  6. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures About the authors Who we are Conceives a Evaluates Delivers a Security Commercialises the component Security Claims Certification certified product Developer ITSEF ANSSI Developer French Certification Scheme Cécile Emmanuel (today) Eleonora 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 2/26

  7. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures About the authors Who we are Conceives a Evaluates Delivers a Security Commercialises the component Security Claims Certification certified product Developer ITSEF ANSSI Developer French Certification Scheme Cécile Emmanuel (today) Eleonora An evaluation point of view ◮ profiling attacks (worst-case security) ◮ practical aspects are concerned 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 2/26

  8. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Contents 1. Context and Motivation 2. A machine learning approach to classification 2.1 Introduction 2.2 Convolutional Neural Networks 3. Data Augmentation 4. Experimental Results 5. Conclusions 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 3/26

  9. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  10. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X Pr [ Z | X ] 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  11. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X Pr [ Z | X ] Template Attacks ◮ Profiling phase (using profiling traces under known Z ) ◮ Attack phase ( N attack traces, e.g. with known plaintexts p i ) Log-likelihood score for each key hypothesis k N � d k = log Pr [ X = x i | Z = f ( p i , k )] i =1 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  12. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X Pr [ Z | X ] Template Attacks ◮ Profiling phase (using profiling traces under known Z ) ◮ estimate Pr [ X | Z = z ] for each value of z ◮ Attack phase ( N attack traces, e.g. with known plaintexts p i ) Log-likelihood score for each key hypothesis k N � d k = log Pr [ X = x i | Z = f ( p i , k )] i =1 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  13. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X Pr [ Z | X ] Template Attacks ◮ Profiling phase (using profiling traces under known Z ) ◮ estimate Pr [ X | Z = z ] for each value of z ◮ Attack phase ( N attack traces, e.g. with known plaintexts p i ) ◮ Log-likelihood score for each key hypothesis k N � d k = log Pr [ X = x i | Z = f ( p i , k )] i =1 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  14. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X Pr [ Z | X ] Template Attacks ◮ Profiling phase (using profiling traces under known Z ) ◮ mandatory dimensionality reduction ◮ estimate Pr [ X | Z = z ] for each value of z ◮ Attack phase ( N attack traces, e.g. with known plaintexts p i ) ◮ Log-likelihood score for each key hypothesis k N � d k = log Pr [ X = x i | Z = f ( p i , k )] i =1 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  15. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Side Channel Attacks Notations ◮ X side channel trace ◮ Z target (a cryptographic sensitive variable Z = f ( P , K )) Goal: make inference over Z , observing X Pr [ Z | X ] Template Attacks ◮ Profiling phase (using profiling traces under known Z ) ◮ manage de-synchronization problem ◮ mandatory dimensionality reduction ◮ estimate Pr [ X | Z = z ] for each value of z ◮ Attack phase ( N attack traces, e.g. with known plaintexts p i ) ◮ Log-likelihood score for each key hypothesis k N � d k = log Pr [ X = x i | Z = f ( p i , k )] i =1 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 4/26

  16. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Misalignment Misaligning Countermeasures ◮ Random Delays, Clock Jittering, ... ◮ In theory: insufficient to provide security, since information still leak (somewhere) ◮ In practice: one of the main issues for evaluators 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 5/26

  17. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Misalignment Misaligning Countermeasures ◮ Random Delays, Clock Jittering, ... ◮ In theory: insufficient to provide security, since information still leak (somewhere) ◮ In practice: one of the main issues for evaluators Realignment Mandatory realignment preprocessing ◮ not a wide literature ◮ in practice: evaluation labs home-made realignment techniques 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 5/26

  18. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Risks of realignment An example 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 6/26

  19. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Risks of realignment An example 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 6/26

  20. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Risks of realignment An example 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 6/26

  21. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Risks of realignment An example 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 6/26

  22. Convolutional Neural Networks with Data Augmentation against Jitter-Based Countermeasures Risks of realignment An example 26/09/2017, CHES 2017, Taipei, Taiwan | E. Cagli, C. Dumas, E. Prouff | 6/26

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Augmentation Introduction ImageNet Classification with Deep Convolutional Neural Networks,

Augmentation Introduction ImageNet Classification with Deep Convolutional Neural Networks,

Day 2 Lecture 2 Augmentation Introduction ImageNet Classification with Deep Convolutional Neural Networks, Krizhevsky A., 2012 ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) 1.2 million training images , 50,000 validation images, and

537 views • 14 slides
Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What

Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What

Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What well cover ... f ( x ) computer vision architectures - convolutional networks - data augmentation 1 - residual networks ... ...

1.29k views • 75 slides
Convolutional Neural Networks ---- Off the shelf top notch performances Convolutional Neural

Convolutional Neural Networks ---- Off the shelf top notch performances Convolutional Neural

Transfer Learning with Convolutional Neural Networks ---- Off the shelf top notch performances Convolutional Neural Networks A breakthough Convolutional Neural Networks VGG-16 example Layers of Convolutional filters Bottleneck

625 views • 23 slides
Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN)

Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN)

Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN) A.k.a. CNN or ConvNet Adit Deshpande, A Beginner's Guide To Understanding Convolutional Neural Networks. Digital Images Input array: an images

1.42k views • 72 slides
Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly

Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly

Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly used for what sort of task? a) Recognizing images b) Transcribing speech c) Translating documents d) Playing games Neural network review

431 views • 13 slides
CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views • 86 slides
Convolutional Neural Networks 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing

Convolutional Neural Networks 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing

Convolutional Neural Networks 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing 2016 Prof. Luiz Velho Convolutional Neural Networks 1 Summary & References 08/11 ImageNet Classification with Deep Convolutional Neural Networks

648 views • 26 slides
and Inference for Convolutional Neural Networks 1 2 FFT IFFT 3 4 Mathieu et al.: Fast

and Inference for Convolutional Neural Networks 1 2 FFT IFFT 3 4 Mathieu et al.: Fast

Band-limited Training and Inference for Convolutional Neural Networks 1 2 FFT IFFT 3 4 Mathieu et al.: Fast Training of Convolutional Networks through FFTs Fast Convolutional Nets With fbfft: A GPU Performance Evaluation Data: x

648 views • 46 slides
MICROBOONE Taritree Wongjirad DPF 2017 Tufts/MIT Outline Convolutional neural networks

MICROBOONE Taritree Wongjirad DPF 2017 Tufts/MIT Outline Convolutional neural networks

Run 3493 Event 41075, Oct. 23rd, 2015 CONVOLUTIONAL NEURAL NETWORKS IN MICROBOONE Taritree Wongjirad DPF 2017 Tufts/MIT Outline Convolutional neural networks (CNNs) are a type of deep, feed-forward neural networks that have been

831 views • 43 slides
Convolutional Neural Networks (Part III) 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image

Convolutional Neural Networks (Part III) 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image

Convolutional Neural Networks (Part III) 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing 2016 Prof. Luiz Velho Convolutional Neural Networks 1 Summary & References 08/11 ImageNet Classification with Deep Convolutional

444 views • 27 slides
Convolutional Neural Networks Rachel Hu and Zhi Zhang Amazon AI d2l.ai Outline GPUs

Convolutional Neural Networks Rachel Hu and Zhi Zhang Amazon AI d2l.ai Outline GPUs

Convolutional Neural Networks Rachel Hu and Zhi Zhang Amazon AI d2l.ai Outline GPUs Convolutions Pooling, Padding and Stride Convolutional Neural Networks (LeNet) Deep ConvNets (AlexNet) Networks using Blocks (VGG)

1.91k views • 89 slides
Convolutional Neural Networks in Speech Lecture 20 CS 753 Instructor: Preethi Jyothi

Convolutional Neural Networks in Speech Lecture 20 CS 753 Instructor: Preethi Jyothi

Convolutional Neural Networks in Speech Lecture 20 CS 753 Instructor: Preethi Jyothi Convolutional Neural Networks (CNNs) Fully connected (dense) layers have no awareness of spatial information Key concept behind convolutional layers is

983 views • 41 slides
Introduction CSCE 970 CSCE 970 Lecture 4: Lecture 4: Convolutional Convolutional Neural

Introduction CSCE 970 CSCE 970 Lecture 4: Lecture 4: Convolutional Convolutional Neural

Introduction CSCE 970 CSCE 970 Lecture 4: Lecture 4: Convolutional Convolutional Neural Neural CSCE 970 Lecture 4: Networks Networks Good for data with a grid-like topology Stephen Scott Convolutional Neural Networks Stephen Scott

355 views • 3 slides
Sequential Data with Neural Networks Recurrent Neural Networks Sequential input / output Greg

Sequential Data with Neural Networks Recurrent Neural Networks Sequential input / output Greg

Recurrent Neural Networks Long Short-Term Memory Temporal Convolutional Networks Examples Recurrent Neural Networks Long Short-Term Memory Temporal Convolutional Networks Examples Sequential Data with Neural Networks Recurrent Neural

303 views • 4 slides
Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) L1 Scalar Processor L0

Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) L1 Scalar Processor L0

Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) L1 Scalar Processor L0 L0 M*V Processor N N N N N N Project Brainwave Pretrained DNN Model Scalable DNN Hardware Neural Processing Unit Microservice Extract

525 views • 30 slides
Convolutional Neural Networks Convolutional neural networks One of the major kinds of ANNs in use

Convolutional Neural Networks Convolutional neural networks One of the major kinds of ANNs in use

Convolutional Neural Networks<br/><br/> 5/4/19, 4(03 PM Convolutional Neural Networks<br/><br/> 5/4/19, 4(03 PM Convolutional Neural Networks Convolutional neural networks One of the major kinds of ANNs in use UMaine

412 views • 9 slides
A Coinductive Monad for Prop -bounded Recursion Adam Megacz megacz@cs.berkeley.edu PLPV07

A Coinductive Monad for Prop -bounded Recursion Adam Megacz megacz@cs.berkeley.edu PLPV07

A Coinductive Monad for Prop -bounded Recursion Adam Megacz megacz@cs.berkeley.edu PLPV07 October 5th, 2007 Freiburg, Germany Entire Talk In One Slide Coqs type theory can directly represent side-effect free, obviously-terminating

970 views • 63 slides
CS415: Systems programming Abdullah Alfarrarjeh Most of the slides in this lecture are either

CS415: Systems programming Abdullah Alfarrarjeh Most of the slides in this lecture are either

CS415: Systems programming Abdullah Alfarrarjeh Most of the slides in this lecture are either from or adapted from the slides provided by Dr. Ahmad Barghash A computer system Is a collection of hardware and software components that work

248 views • 24 slides
Augmenting Stack Overflow with API Usage Patterns Mined from GitHub Anastasia Reinhart 1,2 *

Augmenting Stack Overflow with API Usage Patterns Mined from GitHub Anastasia Reinhart 1,2 *

Augmenting Stack Overflow with API Usage Patterns Mined from GitHub Anastasia Reinhart 1,2 * Tianyi Zhang 1 Mihir Marthur 1 Miryung Kim 1 1 University of California, Los Angeles 2 George Fox University * Work done as a research intern at UCLA. 1

821 views • 35 slides
detection analysis Bradley J. Kavanagh University of Nottingham arXiv:1207.2039 with Anne M.

detection analysis Bradley J. Kavanagh University of Nottingham arXiv:1207.2039 with Anne M.

Improving dark matter direct detection analysis Bradley J. Kavanagh University of Nottingham arXiv:1207.2039 with Anne M. Green Speed dependence Speed dependence dR ~ ( ) v min dE R Speed dependence dR ~ ( ) v min dE

418 views • 38 slides
CS137: Today Electronic Design Automation Multilevel Synthesis/Optimization Why

CS137: Today Electronic Design Automation Multilevel Synthesis/Optimization Why

CS137: Today Electronic Design Automation Multilevel Synthesis/Optimization Why Transforms -- defined Day 5: October 7, 2005 Division/extraction Multi-level Synthesis How we support transforms Boolean Division

358 views • 9 slides
DRM obfuscation vs auxiliary attacks Show me your trace and Ill tell you who you are REcon

DRM obfuscation vs auxiliary attacks Show me your trace and Ill tell you who you are REcon

DRM obfuscation vs auxiliary attacks Show me your trace and Ill tell you who you are REcon 2014 Introduction First layer: Code flattening pTra Algorithm reconstruction : RSA-OAEP Rebuilding a cipher function whiteboxed : AES-CBC

1.43k views • 103 slides
An Analytical Framework for Particle and Volume Data of Large-Scale Combustion Simulations Franz

An Analytical Framework for Particle and Volume Data of Large-Scale Combustion Simulations Franz

An Analytical Framework for Particle and Volume Data of Large-Scale Combustion Simulations Franz Sauer 1 , Hongfeng Yu 2 , Kwan-Liu Ma 1 1 University of California, Davis 2 University of Nebraska, Lincoln Introduction Detailed combustion

484 views • 27 slides
W HAT IS DAA? 1 S ECURITY M ODEL OF DAA 2 A B LUEPRINT FOR DAA 3 ROM I NSTANTIATIONS 4 S

W HAT IS DAA? 1 S ECURITY M ODEL OF DAA 2 A B LUEPRINT FOR DAA 3 ROM I NSTANTIATIONS 4 S

D IRECT A NONYMOUS A TTESTATION Essam Ghadafi ghadafi@cs.bris.ac.uk Department of Computer Science, University of Bristol Brown Univeristy 14 th March - 2013 D IRECT A NONYMOUS A TTESTATION O UTLINE W HAT IS DAA? 1 S ECURITY M ODEL OF DAA

1.06k views • 71 slides

More recommend