Proper Network Interpretability Helps Adversarial Robustness in Classification
12. července 2020
Řečníci
Akhilan Boopathy
Řečník · 0 sledujících
Gaoyuan Zhang
Řečník · 0 sledujících
Cynthia Liu
Řečník · 0 sledujících
Pin-Yu Chen
Řečník · 3 sledující
Shiyu Chang
Řečník · 0 sledujících
Luca Daniel
Řečník · 0 sledujících
O prezentaci
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), and interpretability is itself susceptible to adversarial attacks. In this paper, we theoretically show that with a proper measurement of interpretation, it is actually difficult to prevent prediction-evasion adversarial attacks from causing interpretability discrepancy, as confirmed by experiments on MNIST, CIFAR-10 and Restricted ImageNet. Spurred by that, we develop an interpretability-aware defensive scheme built only on robust interpretation (without the need of resorting to adversarial loss minimization). We show that our defense achieves both robust classification and robust interpretation, outperforming state-of-the-art adversarial training methods against attacks of large perturbation in particular.Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), and interpretability is itself susceptible to adversarial attacks. In this paper, we theoretically show that with a proper measurement of interpretation, it is actually difficult to prevent prediction-evasion adversarial attacks from causing interpretability discrepancy, as confirmed by experiments on MNIS…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (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.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Min-Max Optimization without Gradients: Convergence and Applications
Zhlédnout později
Sijia Liu, …
Unique Properties of Wide Minima in Deep Networks
Zhlédnout později
Predicting Mean Ribosome Load for 5'UTR of any Length using Deep Learning
Zhlédnout později
Private Counting from Anonymous Messages: Near-Optimal Accuracy & Vanishing Communication Overhead
Zhlédnout později
Badih Ghazi, …
The Unsung Heroes of Music Recommendation
Zhlédnout později
