mlsanityData to 7 Oct 2026

Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization

arXiv 2310.08177 ↗First posted 12 Oct 2023cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the loss function, the optimizer and the step-size scheduler, along with the corresponding hyperparameters. Our extensive evaluation involving several robust models demonstrates the improved efficacy of fast minimum-norm attacks when hyper-up with hyperparameter optimization. We release our open-source code at https://github.com/pralab/HO-FMN.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 14 of its 16 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

14 of 16 references.

References · 14

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  4. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  5. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  6. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  7. 2021Improving Robustness using Generated Datacited by 233
  8. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  9. 2018A System for Massively Parallel Hyperparameter Tuningcited by 201
  10. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  11. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  12. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
2 more
  1. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  2. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Natural Language Induced Adversarial Imagescited by 4
  2. 2025Stop Walking in Circles! Bailing Out Early in Projected Gradient Descentcited by 2
  3. 2025Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attackcited by 1
  4. 2024HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attackscited by 0