welcome aro workshop on adversarial learning
play

Welcome: ARO Workshop on Adversarial Learning Palo Alto, CA - PowerPoint PPT Presentation

Aug 06, 2023 •254 likes •390 views

Institute for Network and Security Research Welcome: ARO Workshop on Adversarial Learning Palo Alto, CA September 14, 2017 Patrick McDaniel, Dan Boneh, Kamalika Chaudhuri, David Evans, Somesh Jha, Dawn Song, Ananthram Swami Institute for

  1. Institute for Network and Security Research Welcome: ARO Workshop on Adversarial Learning Palo Alto, CA – September 14, 2017 Patrick McDaniel, Dan Boneh, Kamalika Chaudhuri, David Evans, Somesh Jha, Dawn Song, Ananthram Swami Institute for Network and Security Research 1 Institute for Network and Security Research

  2. Welcome to the ARO Workshop! • On behalf of the event organizers and our colleagues at the Army Research Office, we would like to welcome you to this workshop on adversarial machine learning ... Institute for Network and Security Research Page 2

  3. Thanks … • We wish to ‣ Cliff Wang of ARO, who has tirelessly supported this workshop ‣ Ruth Harris of Stanford University who assisted Frankie ‣ Judy Bowes of Penn State University, who has worked behind the scenes to help coordinate the proposal and initial setup ‣ University staff, catering and other folks … ‣ Student volunteers … ‣ Speakers .. Institute for Network and Security Research Page 3

  4. Todays Agenda Highlights ... Thursday, September 14 th , 2017 9:15 Welcome and overview 9:30-10:15 Ian Goodfellow, Google 10:15-10:45 Jacob Steinhardt, Stanford 10:45-11:00 Break 11:00-11:30 Nicolas Papernot, Penn State 11:30-12:00 Aleksander Madry, MIT 12:00-12:30 Tian Pham, ARL 12:30-14:00 Lunch (provided, in room) … 16:30-16:35 Closing Institute for Network and Security Research Page 4

  5. Todays Agenda (cont.) ... Thursday, September 14 th , 2017 … 12:30-14:00 Lunch 14:00-15:00 Breakouts I 15:00-15:30 Breakouts II 15:30-16:00 Dawn Song, UC Berkeley 16:00-16:30 Dave Evans, Virginia 16:30-16:35 Closing Institute for Network and Security Research Page 5

  6. Breakouts (2-3pm) • 6 different technical sessions (2 sessions of 3) spanning topics of interest collected from the attendees • Rules ‣ Pick and choose what interests you … ‣ No presentations … (workshop rules) ‣ Active participation ... it is on you ‣ Be constructive, listen (self promotion should be limited) ‣ Come and go as you like … try more than one if you want ‣ Have fun, meet people, learn and get new ideas • Q: What are the key challenges and research areas? Institute for Network and Security Research Page 6

  7. Breakouts • 14:00-14:30 ‣ Privacy (Jha, Papernot) ‣ Measuring and achieving resilience (Evans, Grosse) ‣ Fairness (Chaudhuri, ???) • 14:30-15:00 ‣ Autonomous cyber defense (Swami, Grosse) ‣ Adversarial reinforcement learning (Wellman, …) ‣ Attacks on training attacks (Boneh, …) Institute for Network and Security Research Page 7

  8. Machine Learning • Perhaps no area of computer science has had more impact on systems and society in the last 5 years than machine learning ‣ Analytics ‣ Autonomous systems ‣ Vision … Institute for Network and Security Research Page

  9. Focus: Security and Privacy in ML • Challenge: what are the security and privacy challenges of the use of machine learning in adversarial settings? ‣ Fundamental science: • What are the limits of machine learning with respect to accuracy and resilience? • What vulnerabilities are general vs. those are a consequence of the techniques used? • Can the advantages of ML be realized while preserving privacy? ‣ Applied science • What countermeasures are likely to be effective in practice? • What are the domain specific challenges and safeguards for security and privacy? • Ethics: ‣ Just because a system may be able to understand environment, should it? ‣ Can the advantages of ML be realized fairly without discriminating minorities? • Education (what and how to integrate security into machine learning/security courses) Institute for Network and Security Research Page 9

  10. Institute for Network and Security Research Welcome: ARO Workshop on Adversarial Learning (Closing) Palo Alto, CA – September 14, 2017 Patrick McDaniel, Dan Boneh, Kamalika Chaudhuri, David Evans, Somesh Jha, Dawn Song, Ananthram Swami Institute for Network and Security Research 10 Institute for Network and Security Research

  11. Follow on … • Readout: over the next few weeks the organizers will try to capture the substance of the conversations with a focus on the breakouts. • Make a short statement of key areas and challenges faced by the community, as well as identify important application domains. • We will send an email with a reference to the readout to all participants shortly thereafter. • Please send any comments, questions to mcdaniel@cse.psu.edu Institute for Network and Security Research Page

  12. Thanks … • We wish to ‣ Cliff Wang of ARO, who has tirelessly supported this workshop ‣ Ruth Harris of Stanford University who assisted Frankie ‣ Judy Bowes of Penn State University, who has worked behind the scenes to help coordinate the proposal and initial setup ‣ University staff, catering and other folks … ‣ Student volunteers … ‣ Speakers .. • You! Institute for Network and Security Research Page 12

Recommend

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness

Adversarial Approaches to Bayesian Learning and Bayesian Approaches to Adversarial Robustness Ian Goodfellow, OpenAI Research Scientist NIPS 2016 Workshop on Bayesian Deep Learning Barcelona, 2016-12-10 Speculation on Three Topics Can we

769 views • 21 slides
SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY Christian Kaestner with slides from Eunsuk Kang Required reading: Hulten, Geoff. "Building Intelligent Systems: A Guide to Machine Learning

1.95k views • 113 slides
Provably Secure Machine Learning Jacob Steinhardt ARO Adversarial Machine Learning Workshop

Provably Secure Machine Learning Jacob Steinhardt ARO Adversarial Machine Learning Workshop

Provably Secure Machine Learning Jacob Steinhardt ARO Adversarial Machine Learning Workshop September 14, 2017 Why Prove Things? Attackers often have more motivation/resources than defenders Heuristic defenses: arms race between attack and

738 views • 52 slides
Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning

Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning

Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning through Rademacher Complexity Pranjal Awasthi, Natalie Frank, Mehryar Mohri Google Research & Courant Institute August 14, 2020 1 / 17

397 views • 17 slides
Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs

Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs

Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs William Wang 10:30 11:00 Break - 11:00 12:15 Adversarial Examples Sameer Singh 12:15 12:30 Conclusions and Question Answering William

1.75k views • 105 slides
The case for dynamic defenses against adversarial examples Ian Goodfellow SafeML ICLR Workshop

The case for dynamic defenses against adversarial examples Ian Goodfellow SafeML ICLR Workshop

The case for dynamic defenses against adversarial examples Ian Goodfellow SafeML ICLR Workshop 2019-05-06 New Orleans Based on https://arxiv.org/pdf/1903.06293.pdf Definition Adversarial examples are inputs to machine learning models that

411 views • 22 slides
Shrinking and Exploring David Evans University of Virginia Adversarial Search Spaces ARO

Shrinking and Exploring David Evans University of Virginia Adversarial Search Spaces ARO

evadeML. L.org Shrinking and Exploring David Evans University of Virginia Adversarial Search Spaces ARO Workshop on Adversarial Learning Stanford, 14 Sept 2017 Weilin Xu Yanjun Qi Machine Learning is Eating Computer Science 1 Security

552 views • 54 slides
Friendly Adversarial Training: Attacks Which Do Not Kill Training Make Adversarial Learning

Friendly Adversarial Training: Attacks Which Do Not Kill Training Make Adversarial Learning

Friendly Adversarial Training: Attacks Which Do Not Kill Training Make Adversarial Learning Stronger Jingfeng Zhang 1 * , Xilie Xu 2* , Bo Han 34 , Gang Niu 4 , Lichen Cui 5 , Masashi Sugiyama 46 , and Mohan Kankanhalli 1 1 Department of Computer

376 views • 14 slides
Towards Attack-Agnostic Defense for 2D and 3D Recognition Hao Su Workshop on Adversarial Machine

Towards Attack-Agnostic Defense for 2D and 3D Recognition Hao Su Workshop on Adversarial Machine

Towards Attack-Agnostic Defense for 2D and 3D Recognition Hao Su Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems Long Beach, CA, USA 1 Outline Background and Motivation Project-based Defense Mechanism

761 views • 72 slides
AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning Florian Tramr November

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning Florian Tramr November

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning Florian Tramr November 14 th 2019 Joint work with Pascal Dupr, Gili Rusak, Giancarlo Pellegrino and Dan Boneh The Future of Ad-Blocking easylist.txt markup

612 views • 23 slides
CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial

CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial

CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial Learning 1 / 26 Overview Two topics for today: Adversarial examples: examples carefully crafted to cause an undesirable behavior (e.g.

412 views • 26 slides
Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is a type of neural net, used in deep learning/machine learning problems The goal of a GAN is to train two simultaneous models: a generative model

441 views • 18 slides
Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes & George

Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes & George

Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes & George Danezis UCL Adversarial examples transfer between different models. An adversarial example crafted against one model will generally fool other models.

515 views • 18 slides
Controllable Invariance through Adversarial Feature Learning Qizhe Xie, Zihang Dai, Yulun Du,

Controllable Invariance through Adversarial Feature Learning Qizhe Xie, Zihang Dai, Yulun Du,

Controllable Invariance through Adversarial Feature Learning Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy, Graham Neubig Carnegie Mellon University Language Technologies Institute NIPS 2017 Outline Introduction Introduction Adversarial

308 views • 11 slides
Vulnerability of machine learning models to adversarial examples Petra Vidnerov Institute of

Vulnerability of machine learning models to adversarial examples Petra Vidnerov Institute of

Vulnerability of machine learning models to adversarial examples Petra Vidnerov Institute of Computer Science The Czech Academy of Sciences Hora Informaticae 2016 Outline Introduction Works on adversarial examples Our work Genetic

855 views • 46 slides
Adversarial Examples and Adversarial Training Innova&ve Technology Leader program January 22

Adversarial Examples and Adversarial Training Innova&ve Technology Leader program January 22

Adversarial Examples and Adversarial Training Innova&ve Technology Leader program January 22 nd 2018 Florian Tramr Stanford Deep Learning is Super Smart! 2 Is it really? + . 007 = Im sure this Im certain this is a panda is

452 views • 12 slides
Adversarial Domain Adaptation and Adversarial Robustness Judy Hoffman + = Big Deep success

Adversarial Domain Adaptation and Adversarial Robustness Judy Hoffman + = Big Deep success

Adversarial Domain Adaptation and Adversarial Robustness Judy Hoffman + = Big Deep success data learning Benchmark Performance 100 95 Accuracy 90 85 Millions of Images 80 Deep models 75 Challenge to recognize 1000

1.2k views • 60 slides
Adversarial Machine Learning (AML) Somesh Jha University of Wisconsin, Madison Thanks to

Adversarial Machine Learning (AML) Somesh Jha University of Wisconsin, Madison Thanks to

Adversarial Machine Learning (AML) Somesh Jha University of Wisconsin, Madison Thanks to Nicolas Papernot, Ian Goodfellow, and Jerry Zhu for some slides . Machine learning brings social disruption at scale Healthcare Energy Source: Peng and

821 views • 71 slides
Physical Adversarial Examples Alex Kurakin Ian Goodfellow Output STOP Machine Learning

Physical Adversarial Examples Alex Kurakin Ian Goodfellow Output STOP Machine Learning

Physical Adversarial Examples Alex Kurakin Ian Goodfellow Output STOP Machine Learning Training Examples Hidden units / BICYCLE features CAR PEDESTRIA N Parameters Input ImageNet (Russakovsky et al 2015) Adversarial Examples: Images

369 views • 19 slides
LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning and Energy-Based models Suwon Suh POSTECH MLG Feb, 13, 2017 Goal Understanding Basic Models 1) Generative Adversarial Networks (GAN) 2)

722 views • 12 slides
Adversarial Robustness: Theory and Practice Zico Kolter Aleksander Mdry madry-lab.ml

Adversarial Robustness: Theory and Practice Zico Kolter Aleksander Mdry madry-lab.ml

Adversarial Robustness: Theory and Practice Zico Kolter Aleksander Mdry madry-lab.ml Tutorial website: @zicokolter @aleks_madry adversarial-ml-tutorial.org Machine Learning: The Success Story Image classification Reinforcement Learning

528 views • 49 slides
Maximum Entropy Inverse RL, Adversarial imitation learning Katerina Fragkiadaki Reinforcement

Maximum Entropy Inverse RL, Adversarial imitation learning Katerina Fragkiadaki Reinforcement

Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Maximum Entropy Inverse RL, Adversarial imitation learning Katerina Fragkiadaki Reinforcement Learning Probability Dynamics distribution over next Model T

911 views • 66 slides
Maximum Entropy Inverse RL, Adversarial imitation learning Katerina Fragkiadaki Reinforcement

Maximum Entropy Inverse RL, Adversarial imitation learning Katerina Fragkiadaki Reinforcement

Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Maximum Entropy Inverse RL, Adversarial imitation learning Katerina Fragkiadaki Reinforcement Learning Probability Dynamics distribution over next Model T

608 views • 56 slides
Machine Learning Components Shakiba Yaghoubi, Georgios Fainekos CPS V&V I&F Workshop

Machine Learning Components Shakiba Yaghoubi, Georgios Fainekos CPS V&V I&F Workshop

Gray-box Adversarial Testing for Control Systems with Machine Learning Components Shakiba Yaghoubi, Georgios Fainekos CPS V&V I&F Workshop Dec. 11, 2019 @ 1 Accidents happen - IFCS 2 [1] Tomayko, The story of Self-Repairing

1.08k views • 35 slides

More recommend