Adversarial Robustness Against the Union of Multiple Petrubation Models
Jul 12, 2020
Speakers
Pratyush Maini
Speaker · 1 follower
Zico Kolter
Speaker · 2 followers
About
Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of attack, recent work has looked at defending against multiple threat models using simple aggregations of multiple attacks. However, these methods can be difficult to tune, and can easily result in imbalanced degrees of robustness to individual threat models, resulting in a sub-optimal worst-case loss over the combined threat model. In this work, we develop a natural generalization of the standard PGD-based procedure to incorporate multiple threat models into a single attack, by taking the worst-case over all steepest descent directions. This approach has the advantage of directly converging upon a trade-off between different threat models which minimizes the worst-case performance over the union. With this approach, we are able to train standard architectures which are simultaneously robust against l_∞, l_2, and l_1 attacks, outperforming past approaches on the MNIST and CIFAR10 datasets and achieving adversarial accuracy of 46.1Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of attack, recent work has looked at defending against multiple threat models using simple aggregations of multiple attacks. However, these methods can be difficult to tune, and can easily result in imbalanced degrees of robustness to individual threat models, result…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Online Learning with Dependent Stochastic Feedback Graphs
Watch later
WiML Diversity and Inclusion Chairs
Watch later
(Locally) Differentially Private Combinatorial Semi-Bandits
Watch later
Xiaoyu Chen, …
Working Memory Graphs
Watch later
Ricky Loynd, …
Deep Active Learning Toward Crisis-related Tweets Classification
Watch later
