Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916661969289216 |
|---|---|
| author | Doldo, Philip Everett, Derek Khanna, Amol Nguyen, Andre T Raff, Edward |
| author_facet | Doldo, Philip Everett, Derek Khanna, Amol Nguyen, Andre T Raff, Edward |
| contents | Projected Gradient Descent (PGD) under the $L_\infty$ ball has become one of the defacto methods used in adversarial robustness evaluation for computer vision (CV) due to its reliability and efficacy, making a strong and easy-to-implement iterative baseline. However, PGD is computationally demanding to apply, especially when using thousands of iterations is the current best-practice recommendation to generate an adversarial example for a single image. In this work, we introduce a simple novel method for early termination of PGD based on cycle detection by exploiting the geometry of how PGD is implemented in practice and show that it can produce large speedup factors while providing the \emph{exact} same estimate of model robustness as standard PGD. This method substantially speeds up PGD without sacrificing any attack strength, enabling evaluations of robustness that were previously computationally intractable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent Doldo, Philip Everett, Derek Khanna, Amol Nguyen, Andre T Raff, Edward Computer Vision and Pattern Recognition Machine Learning Projected Gradient Descent (PGD) under the $L_\infty$ ball has become one of the defacto methods used in adversarial robustness evaluation for computer vision (CV) due to its reliability and efficacy, making a strong and easy-to-implement iterative baseline. However, PGD is computationally demanding to apply, especially when using thousands of iterations is the current best-practice recommendation to generate an adversarial example for a single image. In this work, we introduce a simple novel method for early termination of PGD based on cycle detection by exploiting the geometry of how PGD is implemented in practice and show that it can produce large speedup factors while providing the \emph{exact} same estimate of model robustness as standard PGD. This method substantially speeds up PGD without sacrificing any attack strength, enabling evaluations of robustness that were previously computationally intractable. |
| title | Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.19347 |