mlsanityData to 14 Oct 2026

HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks

arXiv 2407.08806 ↗First posted 11 Jul 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed loss functions, optimizers, step-size schedulers, and default hyperparameters. In this work, we tackle these limitations by proposing a parametric variation of the well-known fast minimum-norm attack algorithm, whose loss, optimizer, step-size scheduler, and hyperparameters can be dynamically adjusted. We re-evaluate 12 robust models, showing that our attack finds smaller adversarial perturbations without requiring any additional tuning. This also enables reporting adversarial robustness as a function of the perturbation budget, providing a more complete evaluation than that offered by fixed-budget attacks, while remaining efficient. We release our open-source code at https://github.com/pralab/HO-FMN.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 27 references that are in the map. First posted on arXiv 11 Jul 2024.

Builds on

25 of 27 references.

References · 25

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  6. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  7. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  8. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  9. 2019On Evaluating Adversarial Robustnesscited by 447
  10. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  11. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  12. 2021Improving Robustness using Generated Datacited by 234
13 more
  1. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  2. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 204
  3. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  4. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 111
  5. 2017Constrained Bayesian Optimization with Noisy Experimentscited by 104
  6. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  7. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  8. 2020Curse of Dimensionality on Randomized Smoothing for Certifiable Robustnesscited by 56
  9. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  10. 2021Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examplescited by 23
  11. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22
  12. 2020Initial Design Strategies and their Effects on Sequential Model-Based Optimizationcited by 10
  13. 2023Improving Fast Minimum-Norm Attacks with Hyperparameter Optimizationcited by 4

Built on by

Not cited yet.