Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks
Jul 12, 2020
Speakers
Yonggang Zhang
Speaker · 0 followers
Tongliang Liu
Speaker · 0 followers
Xinmei Tian
Speaker · 0 followers
About
We study the problem of constructing adversarial examples in the black-box setting, where no model information is revealed except the feedback knowledge of given inputs. To obtain sufficient knowledge for crafting adversarial examples, previous methods query the target model with inputs that are perturbed with different searching directions. However, these methods suffer from poor query efficiency since the employed searching directions are sampled randomly. To mitigate the issue, we capture the goal of mounting efficient attacks as an optimization problem that the adversary tries to fool the target model with limited queries. In such setting, the adversary has to select appropriate searching directions to reduce model queries. By solving the efficient-attack problem, we find that what we need is to distill the knowledge in both the adversarial example path and the searching direction path. Therefore, we propose a novel framework, dual-path distillation, that utilizes the feedback knowledge not only to craft adversarial examples but also alter searching directions for efficient attacks. Experimental results suggest that our framework can significantly increase the query efficiency.We study the problem of constructing adversarial examples in the black-box setting, where no model information is revealed except the feedback knowledge of given inputs. To obtain sufficient knowledge for crafting adversarial examples, previous methods query the target model with inputs that are perturbed with different searching directions. However, these methods suffer from poor query efficiency since the employed searching directions are sampled randomly. To mitigate the issue, we capture the…
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
Sets Clustering
Watch later
Invited Talk 3 Q&A
Watch later
Private Reinforcement Learning with PAC and Regret Guarantees
Watch later
Scalable Nearest Neighbor Search for Optimal Transport
Watch later
Data Valuation using Reinforcement Learning
Watch later
Jinsung Yoon, …