Metraipolis › archive › dc_09af008d7850

FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation — arXiv:2608.26861

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26861
License (as archived)
CC0-1.0
Archived
2026-10-17T15:55:23.724Z
SHA-256 of the archived text
29f112af6aab5665bf08196031051913ec8ce9f9ff67641d7b762e3602abdd27
Stable URL of this page
https://metraipolis.com/documento/dc_09af008d7850

How to cite

FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation — arXiv:2608.26861 — arXiv (en), https://arxiv.org/abs/2608.26861 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09af008d7850 (Metraipolis archive dc_09af008d7850, sha256 29f112af6aab5665bf08196031051913ec8ce9f9ff67641d7b762e3602abdd27)
BibTeX
@misc{dc09af008d7850,
  title = {FIDA: Feature Instability-Driven Attack on Self-Supervised Facial Representation — arXiv:2608.26861},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26861},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09af008d7850; sha256 29f112af6aab5665bf08196031051913ec8ce9f9ff67641d7b762e3602abdd27},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26861. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. However, the systemic risks they pose in face representation have received little attention. The entanglement of identity features in self-supervised face learning presents unique challenges for attack stealthiness. To address this gap, we propose FIDA (Feature Instability-Driven Attack), a novel backdoor attack framework. FIDA uses subtle semantic triggers for injection, but its key innovation is a novel objective called Feature Instability Loss. It trains the encoder to increase the sensitivity of triggered features along perturbation directions sampled during attack optimization . By preventing the backdoor from exhibiting the rigid feature patterns typical of previous attacks, FIDA effectively evades the evaluated perturbation-based defenses. Experiments show that FIDA achieves a high attack success rate and generally preserves benign utility across the evaluated settings , posing a significant threat to real-world multimedia applications relying on facial analysis.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CR).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.26861 — 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 2026-10-17T15:31:38.289Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).