Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

Maura Pintor, Luca Demetrio, Angelo Sotgiu, Giovanni Manca, Ambra Demontis, Nicholas Carlini, Battista Biggio, Fabio Roli

Keywords: adversarial machine learning, machine learning

TL;DR: Analysis of failures in the optimization of adversarial attacks, indicators to reveal when they happen, and systematic framework to avoid them

Abstract: Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of security by causing gradient-based attacks to fail, and they have been broken under more rigorous evaluations. Although guidelines and best practices have been suggested to improve current adversarial robustness evaluations, the lack of automatic testing and debugging tools makes it difficult to apply these recommendations in a systematic manner. In this work, we overcome these limitations by (i) defining a set of quantitative indicators which unveil common failures in the optimization of gradient-based attacks, and (ii) proposing specific mitigation strategies within a systematic evaluation protocol. Our extensive experimental analysis shows that the proposed indicators of failure can be used to visualize, debug and improve current adversarial robustness evaluations, providing a first concrete step towards automatizing and systematizing current adversarial robustness evaluations.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Community Implementations: [ 5 code implementations](https://www.catalyzex.com/paper/indicators-of-attack-failure-debugging-and/code)