Robust Machine Learning Algorithms and Systems for Detection and Mitigation of Adversarial Attacks and Anomalies
Proceedings of a Workshop
1st Edition
Published on 22. August 2019
82 pages
978-0-309-49612-4 (ISBN)
Description
The Intelligence Community Studies Board (ICSB) of the National Academies of Sciences, Engineering, and Medicine convened a workshop on December 1112, 2018, in Berkeley, California, to discuss robust machine learning algorithms and systems for the detection and mitigation of adversarial attacks and anomalies. This publication summarizes the presentations and discussions from the workshop.
More details
Content
- Intro
- TITLE PAGE
- COPYRIGHT PAGE
- TABLE OF CONTENTS
- 1 INTRODUCTION
- 2 PLENARY SESSION
- Sponsor Remarks and Expectations of the Workshop
- On Computational Thinking, Inferential Thinking, and Data Science
- Machine Learning on Perception: Hype vs. Hope
- 3 ADVERSARIAL ATTACKS
- Media Forensics
- Forensic Techniques
- 4 DETECTION AND MITIGATION OF ADVERSARIAL ATTACKS AND ANOMALIES
- Using AI for Security and Securing AI
- Circumventing Defenses to Adversarial Examples
- 5 ENABLERS OF MACHINE LEARNING ALGORITHMS AND SYSTEMS
- Impact of Neuroscience on Data Science for Perception
- 6 RECENT TRENDS IN MACHINE LEARNING, PARTS 1 AND 2
- On Open Set and Adversarial Issues in Machine Learning
- Generative Adversarial Networks (GANs) for Domain Adaptation and Security Against Attacks
- Recent Advances in Optimization for Machine Learning
- Forecasting Using Machine Learning
- 7 PLENARY SESSION
- Toward Trustworthy Machine Learning
- 8 RECENT TRENDS IN MACHINE LEARNING, PART 3
- Domain Adaptation
- Explainable Machine Learning
- 9 MACHINE LEARNING SYSTEMS
- Building Domain-Specific Knowledge with Human-in-the-Loop
- Robust Designs of Machine Learning Systems
- REFERENCES
- APPENDIXES
- A Biographical Sketches of Workshop Planning Committee
- B Workshop Agenda
- C Workshop Statement of Task
- D Capability Technology Matrix
- E Acronyms
