security of deep learning
play

Security of Deep Learning Nicolas Papernot ~ ngp5056@cse.psu.edu - PowerPoint PPT Presentation

Nov 30, 2023 •386 likes •752 views

All parts of this talk should not be further distributed without first contacting the author Security of Deep Learning Nicolas Papernot ~ ngp5056@cse.psu.edu PSU CSE - Dr. Patrick McDaniels lab 1 All parts of this talk should not be further

  1. All parts of this talk should not be further distributed without first contacting the author Security of Deep Learning Nicolas Papernot ~ ngp5056@cse.psu.edu PSU CSE - Dr. Patrick McDaniel’s lab 1

  2. All parts of this talk should not be further distributed without first contacting the author Neuron input input output input input 2

  3. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author Neural Networks 3

  4. All parts of this talk should not be further distributed without first contacting the author Danger! > (Artificial) Neural Networks are far from modeling the brain’s behavior 4

  5. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author Deep Neural Networks 5

  6. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author Deep Neural Networks 6

  7. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author Deep Neural Networks 7

  8. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author Deep Neural Networks 8

  9. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author Deep Neural Networks 9

  10. All parts of this talk should not be further distributed without first contacting the author 10

  11. All parts of this talk should not be further distributed without first contacting the author 11

  12. All parts of this talk should not be further distributed without first contacting the author 12

  13. All parts of this talk should not be further distributed without first contacting the author 13

  14. All parts of this talk should not be further distributed without first contacting the author Speech Recognition as Probabilistic Transduction Language Model Meaning Decision Trees Sentence Word Feature Extraction Phoneme NLP State Frame Lexicon Audio Acoustic Model Source: Tara N. Sainath @ ICML DL Workshop 2015 14

  15. 15

  16. All parts of this talk should not be further distributed without first contacting the author Output classification 0 1 2 3 4 5 6 7 8 9 9 8 7 6 5 4 3 2 1 0 Adversarial Input class Samples 16

  17. All parts of this talk should not be further distributed without first contacting the author 17

  18. All parts of this talk should not be further distributed without first contacting the author 18

  19. All parts of this talk should not be further distributed without first contacting the author Neuron input input output input input 19

  20. All parts of this talk should not be further distributed without first contacting the author Neuron 0 1 m X y = ϕ w j x j @ A j =0 20

  21. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author w 11 h 1 x 1 w 31 w 12 o w 21 w 32 h 2 x 2 w 22 21

  22. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author w 11 h 1 x 1 w 31 w 12 o w 21 w 32 h 2 x 2 w 22 22

  23. All parts of this talk should not be further distributed without first contacting the author 1 0 23

  24. All parts of this talk should not be further distributed without first contacting the author r F ( X ) 24

  25. All parts of this talk should not be further distributed without first contacting the author w 11 h 1 x 1 w 31 w 12 o w 21 w 32 h 2 x 2 w 22 25

  26. All parts of this talk should not be further distributed without first contacting the author X ∗ = (1 , 0 . 43) X = (1 , 0 . 37) 26

  27. All parts of this talk should not be further distributed without first contacting the author F ( X ) = 0 . 11 F ( X ∗ ) = 0 . 95 27

  28. All parts of this talk should not be further distributed without first contacting the author All parts of this talk should not be further distributed without first contacting the author What about Deep Neural Networks? 28

  29. All parts of this talk should not be further distributed without first contacting the author 29

  30. All parts of this talk should not be further distributed without first contacting the author 30,000 30

  31. All parts of this talk should not be further distributed without first contacting the author 270,000 31

  32. All parts of this talk should not be further distributed without first contacting the author 97.10% 32

  33. All parts of this talk should not be further distributed without first contacting the author 4.02% 33

  34. All parts of this talk should not be further distributed without first contacting the author 34

  35. All parts of this talk should not be further distributed without first contacting the author Current Research 35

Recommend

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY MEDIA & ENTERTAINMENT SECURITY & DEFENSE AUTONOMOUS MACHINES Image

311 views • 26 slides
Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice Scaling up DL 2 What is Deep Learning? 3 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY SECURITY & DEFENSE MEDIA &

1.45k views • 39 slides
WITH TECHNOLOGY FACE ATTRIBUTES NETWORK CAMERA WH WHAT AT IS IS DE DEEP EP LEARNING

WITH TECHNOLOGY FACE ATTRIBUTES NETWORK CAMERA WH WHAT AT IS IS DE DEEP EP LEARNING

EPHRAIM SECURITY WITH TECHNOLOGY FACE ATTRIBUTES NETWORK CAMERA WH WHAT AT IS IS DE DEEP EP LEARNING EARNING Artificial Intelligence Machine Learning Deep Learning DEEP COOPERATION BETWEEN EPHRAIM AI & INTEL CPU/FPGA

569 views • 29 slides
Deep Learning For Embedded Security Evaluation Emmanuel PROUFF Joint work with Ryad Benadjila,

Deep Learning For Embedded Security Evaluation Emmanuel PROUFF Joint work with Ryad Benadjila,

Deep Learning For Embedded Security Evaluation Deep Learning For Embedded Security Evaluation Emmanuel PROUFF Joint work with Ryad Benadjila, Eleonora Cagli (CEA LETI), C ecile Dumas (CEA LETI), Houssem Maghrebi (UL), Loic Masure (CEA LETI),

932 views • 71 slides
Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Deep 3D Representation Learning for Visual Computing Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms Conclusion 2 Outline Overview of 3D deep learning Background 3D deep learning tasks 3D deep

1.66k views • 122 slides
A Tour of Machine Learning Security Florian Tramr CISPA August 6 th 2018 The Deep Learning

A Tour of Machine Learning Security Florian Tramr CISPA August 6 th 2018 The Deep Learning

A Tour of Machine Learning Security Florian Tramr CISPA August 6 th 2018 The Deep Learning Revolution First they came for images The Deep Learning Revolution And then everything else The ML Revolution Including things that likely

971 views • 45 slides
The Unspoken Problems With Machine Learning in Security Noa Weiss Hi! AI & Machine Learning

The Unspoken Problems With Machine Learning in Security Noa Weiss Hi! AI & Machine Learning

The Unspoken Problems With Machine Learning in Security Noa Weiss Hi! AI & Machine Learning Consultant Playing with data for over a decade Risk and Security PayPal, Armis 2 Hi! Deep Voice foundation Leader of

554 views • 54 slides
Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning Methods) Peter Henderson Statistical Society of Canada Annual Meeting 2018 Contributors Riashat Islam Phil Bachman Doina Precup David Meger Joelle

850 views • 37 slides
DEEP LEARNING DEMYSTIFIED Will Ramey Director, Developer Programs NVIDIA Corporation

DEEP LEARNING DEMYSTIFIED Will Ramey Director, Developer Programs NVIDIA Corporation

DEEP LEARNING DEMYSTIFIED Will Ramey Director, Developer Programs NVIDIA Corporation DEFINITIONS DEEP LEARNING IS SWEEPING ACROSS INDUSTRIES Internet Services Medicine Media & Entertainment Security & Defense Autonomous Machines

532 views • 24 slides
Efficient Communication Library for Large-Scale Deep Learning Mar 26, 2018 Minsik Cho

Efficient Communication Library for Large-Scale Deep Learning Mar 26, 2018 Minsik Cho

IBM Research AI Efficient Communication Library for Large-Scale Deep Learning Mar 26, 2018 Minsik Cho (minsikcho@us.ibm.com) Deep Learning changing Our Life Automotive/transportation Medicine and Biology Security/public safety Consumer Web,

342 views • 19 slides
How to build privacy and security into deep learning models Yishay Carmiel @YishayCarmiel The

How to build privacy and security into deep learning models Yishay Carmiel @YishayCarmiel The

How to build privacy and security into deep learning models Yishay Carmiel @YishayCarmiel The evolution of AI AI has evolved a lot over the last few years Speech Recognition Computer Vision Machine Translation Natural Language Processing

939 views • 54 slides
Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI Mission Helping people solve challenging problems using AI and deep learning. Developers, data scientists and engineers Self-driving cars,

1.44k views • 72 slides
Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and Courville [chapt. 6,7,8]; AIMA [sect. 21.1-21.3]; Sutton and Barto, Reinforcement Learning: an

527 views • 35 slides
Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin Clark Deep Learning for NLP 5 years ago No Seq2Seq No Attention No large-scale QA/reading comprehension datasets No TensorFlow or

1.41k views • 92 slides
An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning Microsoft Research Asia (MSRA) Kaiming He, Xiangyu Zhang, Shaoqing Ren, & Jian Sun. Deep Residual Learning for Image Recognition. arXiv

1.32k views • 54 slides
Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

541 views • 15 slides
Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning

Mocha.jl Deep Learning in Julia Chiyuan Zhang (@pluskid) CSAIL, MIT Deep Learning Learning with multi-layer (3~30) neural networks, on a huge training set. State-of-the-art on many AI tasks Computer Vision : Image Classification,

1.53k views • 23 slides
Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL

Tofu: Parallelizing Deep Learning Systems with Automatic Tiling Minjie Wang Deep Learning Deep Learning trend in the past 10 years Caffe State-of-art DL system is based on dataflow GPU#0 w1 w2 data g1 g2 Forward propagation

405 views • 38 slides
Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations

Deep Learning: Theory and Practice Deep Learning - Practical 02-04-2020 Considerations deeplearning.cce2020@gmail.com Deep Networks Intuition Neural networks with multiple hidden layers - Deep networks [Hinton, 2006] Deep Networks Intuition

1.33k views • 28 slides
Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu

Deep Learning: State of the Art (2020) Deep Learning Lecture Series https://deeplearning.mit.edu 2020 For the full list of references visit: http://bit.ly/deeplearn-sota-2020 Outline Deep Learning Growth, Celebrations, and Limitations

1.1k views • 87 slides
12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views • 115 slides
Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning

Regularization for Deep Learning Lecture slides for Chapter 7 of Deep Learning www.deeplearningbook.org Ian Goodfellow 2016-09-27 Definition Regularization is any modification we make to a learning algorithm that is intended to reduce

179 views • 13 slides
Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention

Introduction to Deep Learning Outline Deep Learning RNN CNN Attention Transformer Pytorch Introduction Basics Examples RNNs Some slides borrowed from Fei-Fei Li & Justin Johnson &

1.1k views • 55 slides
Deep learning for NLP: Introduction CS 6956: Deep Learning for NLP Words are a very fantastical

Deep learning for NLP: Introduction CS 6956: Deep Learning for NLP Words are a very fantastical

Deep learning for NLP: Introduction CS 6956: Deep Learning for NLP Words are a very fantastical banquet, just so many strange dishes And yet, we seem to do fine We can understand and generate language effortlessly. Almost 1 Wouldnt it be

1.62k views • 52 slides

More recommend