Localizing Adversarial Attacks To Produces More Imperceptible Noise
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_ | 1866918149114298368 |
|---|---|
| author | Reddy, Pavan Gujral, Aditya Sanjay |
| author_facet | Reddy, Pavan Gujral, Aditya Sanjay |
| contents | Adversarial attacks in machine learning traditionally focus on global perturbations to input data, yet the potential of localized adversarial noise remains underexplored. This study systematically evaluates localized adversarial attacks across widely-used methods, including FGSM, PGD, and C&W, to quantify their effectiveness, imperceptibility, and computational efficiency. By introducing a binary mask to constrain noise to specific regions, localized attacks achieve significantly lower mean pixel perturbations, higher Peak Signal-to-Noise Ratios (PSNR), and improved Structural Similarity Index (SSIM) compared to global attacks. However, these benefits come at the cost of increased computational effort and a modest reduction in Attack Success Rate (ASR). Our results highlight that iterative methods, such as PGD and C&W, are more robust to localization constraints than single-step methods like FGSM, maintaining higher ASR and imperceptibility metrics. This work provides a comprehensive analysis of localized adversarial attacks, offering practical insights for advancing attack strategies and designing robust defensive systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Localizing Adversarial Attacks To Produces More Imperceptible Noise Reddy, Pavan Gujral, Aditya Sanjay Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition I.2.6; I.2.10; I.5.1 Adversarial attacks in machine learning traditionally focus on global perturbations to input data, yet the potential of localized adversarial noise remains underexplored. This study systematically evaluates localized adversarial attacks across widely-used methods, including FGSM, PGD, and C&W, to quantify their effectiveness, imperceptibility, and computational efficiency. By introducing a binary mask to constrain noise to specific regions, localized attacks achieve significantly lower mean pixel perturbations, higher Peak Signal-to-Noise Ratios (PSNR), and improved Structural Similarity Index (SSIM) compared to global attacks. However, these benefits come at the cost of increased computational effort and a modest reduction in Attack Success Rate (ASR). Our results highlight that iterative methods, such as PGD and C&W, are more robust to localization constraints than single-step methods like FGSM, maintaining higher ASR and imperceptibility metrics. This work provides a comprehensive analysis of localized adversarial attacks, offering practical insights for advancing attack strategies and designing robust defensive systems. |
| title | Localizing Adversarial Attacks To Produces More Imperceptible Noise |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition I.2.6; I.2.10; I.5.1 |
| url | https://arxiv.org/abs/2509.22710 |