MultiRobustBench: Benchmarking Robustness Against Multiple Attacks

Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin Yu Chen, Prateek Mittal

Research output: Contribution to journalConference articlepeer-review

Abstract

The bulk of existing research in defending against adversarial examples focuses on defending against a single (typically bounded ℓp-norm) attack, but for a practical setting, machine learning (ML) models should be robust to a wide variety of attacks. In this paper, we present the first unified framework for considering multiple attacks against ML models. Our framework is able to model different levels of learner's knowledge about the test-time adversary, allowing us to model robustness against unforeseen attacks and robustness against unions of attacks. Using our framework, we present the first leaderboard, MultiRobustBench (https://multirobustbench.github.io), for benchmarking multiattack evaluation which captures performance across attack types and attack strengths. We evaluate the performance of 16 defended models for robustness against a set of 9 different attack types, including ℓp-based threat models, spatial transformations, and color changes, at 20 different attack strengths (180 attacks total). Additionally, we analyze the state of current defenses against multiple attacks. Our analysis shows that while existing defenses have made progress in terms of average robustness across the set of attacks used, robustness against the worst-case attack is still a big open problem as all existing models perform worse than random guessing.

Original languageEnglish (US)
Pages (from-to)6760-6785
Number of pages26
JournalProceedings of Machine Learning Research
Volume202
StatePublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: Jul 23 2023Jul 29 2023

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'MultiRobustBench: Benchmarking Robustness Against Multiple Attacks'. Together they form a unique fingerprint.

Cite this