1

Evading Black-box Classifiers Without Breaking Eggs

We propose a new real-world oriented metric for black-box decision-based attacks on security-critical systems

Edoardo Debenedetti, Nicholas Carlini, Florian Tramèr

A Light Recipe to Train Robust Vision Transformers

This paper shows that ViTs are highly suitable for adversarial training to achieve competitive performance and recommends that the community should avoid translating the canonical training recipes in ViTs to robust training and rethink common training choices in the context of adversarial training.

Edoardo Debenedetti, Vikash Sehwag, Prateek Mittal

RobustBench: A standardized benchmark for adversarial robustness

As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it …

Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein