Optimization for Robustness Evaluation beyond ℓp Metrics
Not on the map. Why?
Abstract (arXiv)
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems. Popular algorithms for solving these constrained problems rely on projected gradient descent (PGD) and require careful tuning of multiple hyperparameters. Moreover, PGD can only handle ℓ1, ℓ2, and ℓ_∞ attack models due to the use of analytical projectors. In this paper, we introduce a novel algorithmic framework that blends a general-purpose constrained-optimization solver PyGRANSO, With Constraint-Folding (PWCF), to add reliability and generality to robustness evaluation. PWCF 1) finds good-quality solutions without the need of delicate hyperparameter tuning, and 2) can handle general attack models, e.g., general ℓp (p ≥ 0) and perceptual attacks, which are inaccessible to PGD-based algorithms.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 2 Oct 2022.
Builds on
22 of 33 references.
References · 22
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
- 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
- 2018Spatially Transformed Adversarial Examplescited by 195
- 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
- 2019Sparse and Imperceivable Adversarial Attackscited by 95
10 more
- 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
- 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
- 2018Semantic Adversarial Examplescited by 86
- 2019Functional Adversarial Attackscited by 82
- 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 76
- 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
- 2018Logit Pairing Methods Can Fool Gradient-Based Attackscited by 27
- 2018Gradient Sampling Methods for Nonsmooth Optimizationcited by 23
- 2019GENO -- GENeric Optimization for Classical Machine Learningcited by 12
- 2021NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learningcited by 5
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.
3 papers.