Metraipolis › archive › dc_ef7252b0725f
Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining — arXiv:2608.03101
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03101
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:58:12.866Z
- SHA-256 of the archived text
29afb40e977f45b5a0af0cab7201de00a89e73c3c62c32875de674b7c6a0fb47- Stable URL of this page
https://metraipolis.com/documento/dc_ef7252b0725f
How to cite
Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining — arXiv:2608.03101 — arXiv (en), https://arxiv.org/abs/2608.03101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef7252b0725f (Metraipolis archive dc_ef7252b0725f, sha256 29afb40e977f45b5a0af0cab7201de00a89e73c3c62c32875de674b7c6a0fb47)
BibTeX
@misc{dcef7252b0725f,
title = {Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining — arXiv:2608.03101},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03101},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef7252b0725f; sha256 29afb40e977f45b5a0af0cab7201de00a89e73c3c62c32875de674b7c6a0fb47},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Near-duplicate image matching is crucial for trust and safety, provenance verification, copyright enforcement, and large-scale visual search. Modern platforms increasingly rely on deep perceptual hashes, which map visually similar images to nearby representations despite common image transformations. However, adversarial perturbations can cause near-duplicates to evade matching. We present DualShield, a plug-in defense that improves the robustness of existing deep perceptual hashes without retraining or modifying their underlying models. DualShield combines matching-time randomized smoothing, which aggregates decisions over perturbed reference-query pairs, with publication-time hardening, which adds an optimized imperceptible perturbation to each reference image before publication. Together, these mechanisms provide certified and empirical robustness. DualShield achieves a certified $\ell_2$ radius of approximately 0.3, guaranteeing that query perturbations within this radius cannot evade matching. We further evaluate it against adaptive white-box, black-box, and image-transformation attacks. Across eight deep perceptual hashes and three datasets, DualShield substantially reduces attack success rates while preserving low collision rates. These results show that deep perceptual hashes can be strengthened without costly retraining by improving the matching procedure and hardening reference images before publication. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.03101 — 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 2026-10-31T12:45:33.218Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).