DeepAI AI Chat
Log In Sign Up

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

by   Maura Pintor, et al.

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. Our open-source code is available at:


page 1

page 2

page 3

page 4


Logit Pairing Methods Can Fool Gradient-Based Attacks

Recently, several logit regularization methods have been proposed in [Ka...

RobustBench: a standardized adversarial robustness benchmark

Evaluation of adversarial robustness is often error-prone leading to ove...

On Evaluating Adversarial Robustness

Correctly evaluating defenses against adversarial examples has proven to...

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

We identify obfuscated gradients as a phenomenon that leads to a false s...

Minimum-Norm Adversarial Examples on KNN and KNN-Based Models

We study the robustness against adversarial examples of kNN classifiers ...

Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning

Adversarial attacks on graphs have posed a major threat to the robustnes...

Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles

Attack Ensemble (AE), which combines multiple attacks together, provides...

Code Repositories


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

view repo