Metraipolis › archive › dc_bb6abc91feb7

Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation — arXiv:2611.04939

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04939
License (as archived): CC0-1.0
Archived: 2026-11-04T12:57:08.390Z
SHA-256 of the archived text: c07343990e68fef53432be038cf191d15ad8fe0bae3b7f405bcd10a9e37690ad
Stable URL of this page: https://metraipolis.com/documento/dc_bb6abc91feb7

How to cite

Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation — arXiv:2611.04939 — arXiv (en), https://arxiv.org/abs/2611.04939 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb6abc91feb7 (Metraipolis archive dc_bb6abc91feb7, sha256 c07343990e68fef53432be038cf191d15ad8fe0bae3b7f405bcd10a9e37690ad)

BibTeX

@misc{dcbb6abc91feb7,
  title = {Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation — arXiv:2611.04939},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04939},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb6abc91feb7; sha256 c07343990e68fef53432be038cf191d15ad8fe0bae3b7f405bcd10a9e37690ad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04939. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robustness verification is essential for ensuring the safety and security of neural networks, but current methods focus heavily on norm-ball attacks, which do not adequately model typical real-world threats that present physical perturbations, known as patch attacks. A naive approach requires computationally prohibitive enumeration of all possible patch positions. To address the challenge, we propose a novel neural network verification method specialized to the patch-attack threat. Instead of enumerating patch locations, we first model the patch attack with group-wise sparsity and formulate its verification methods as a mixed-integer semidefinite program (MISDP) by applying SDP relaxation to the neural network. We then propose three relaxations, including Group-Lasso relaxation, that remove the integer variables while preserving the sparse, group-wise structure of the original attack, enabling substantially efficient verification. Our empirical analysis demonstrates that the proposed relaxations require less than 3% of the computation time of the original MISDP, while the Group-Lasso relaxation incurs only a 0.34\% average increase in the objective value over the original formulation. Furthermore, Group-Lasso achieves a verified rate of 91%, compared with under 70% for prior methods.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.04939 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:33:47.194Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).