paper-with-me

Papers

Testing Robustness Against Unforeseen Adversaries

2019-08-21 · Max Kaufmann, Daniel Kang, Yi Sun, Steven Basart, Xuwang Yin, Mantas Mazeika, Akul Arora, Adam Dziedzic, Franziska Boenisch, Tom Brown, Jacob Steinhardt, Dan Hendrycks

Adversarial robustness research primarily focuses on L_p perturbations, and most defenses are developed with identical training-time and test-time adversaries. However, in real-world applications developers are unlikely to have access to the full range of attacks or corruptions their system will face. Furthermore, worst-case inputs are likely to be diverse and need not be constrained to the L_p ball. To narrow in on this discrepancy between research and reality we introduce ImageNet-UA, a framework for evaluating model robustness against a range of unforeseen adversaries, including eighteen new non-L_p attacks. To perform well on ImageNet-UA, defenses must overcome a generalization gap and be robust to a diverse attacks not encountered during training. In extensive experiments, we find that existing robustness measures do not capture unforeseen robustness, that standard robustness techniques are beat by alternative training strategies, and that novel methods can improve unforeseen robustness. We present ImageNet-UA as a useful tool for the community for improving the worst-case behavior of machine learning systems.

📄 PDF Abstract BibTeX arXiv:1908.08016

Code (3)

centerforaisafety/adversarial-corruptions 공식 구현 pytorch
ddkang/advex-uar 공식 구현 pytorch
gatheluck/Stronghold pytorch

Tasks

Adversarial DefenseAdversarial Robustness

Similar Papers 제목 키워드 기반

TSS: Transformation-Specific Smoothing for Robustness Certification

2020-02-27 · Linyi Li, Maurice Weber, Xiaojun Xu, Luka Rimanic 외

As machine learning (ML) systems become pervasive, safeguarding their security is critical. However, recently it has been demonstrated that motivated adversaries are able to mislead ML systems by perturbing test data usi…

Formulating Robustness Against Unforeseen Attacks

2022-04-28 · Sihui Dai, Saeed Mahloujifar, Prateek Mittal

Existing defenses against adversarial examples such as adversarial training typically assume that the adversary will conform to a specific or known threat model, such as $\ell_p$ perturbations within a fixed budget. In t…

Reducing Exploitability with Population Based Training

2022-08-10 · Pavel Czempin, Adam Gleave

Self-play reinforcement learning has achieved state-of-the-art, and often superhuman, performance in a variety of zero-sum games. Yet prior work has found that policies that are highly capable against regular opponents c…

Diversity

Toward Robust Non-Transferable Learning: A Survey and Benchmark

2025-02-19 · Ziming Hong, Yongli Xiang, Tongliang Liu

Over the past decades, researchers have primarily focused on improving the generalization abilities of models, with limited attention given to regulating such generalization. However, the ability of models to generalize …

EthicsSurvey

Certified Defenses for Adversarial Patches

2020-03-14 · ICLR 2020 1 · Ping-Yeh Chiang, Renkun Ni, Ahmed Abdelkader, Chen Zhu 외

Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks. We begin with a set of ex…