Metraipolis › archive › dc_c9dcd82f8ec6

Universal Concept Disruption for SAM3 Image Segmentation — arXiv:2608.05983

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05983
License (as archived)
CC0-1.0
Archived
2026-10-31T10:36:27.120Z
SHA-256 of the archived text
f2129c7ef92ca5663c2b7f24b8ce2e84652dccb33d06b375153e0e882ac315ef
Stable URL of this page
https://metraipolis.com/documento/dc_c9dcd82f8ec6

How to cite

Universal Concept Disruption for SAM3 Image Segmentation — arXiv:2608.05983 — arXiv (en), https://arxiv.org/abs/2608.05983 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9dcd82f8ec6 (Metraipolis archive dc_c9dcd82f8ec6, sha256 f2129c7ef92ca5663c2b7f24b8ce2e84652dccb33d06b375153e0e882ac315ef)
BibTeX
@misc{dcc9dcd82f8ec6,
  title = {Universal Concept Disruption for SAM3 Image Segmentation — arXiv:2608.05983},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05983},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9dcd82f8ec6; sha256 f2129c7ef92ca5663c2b7f24b8ce2e84652dccb33d06b375153e0e882ac315ef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05983. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

SAM3 extends promptable segmentation from geometry-driven mask prediction to open-vocabulary concept segmentation, where a text-conditioned grounding model decides whether a concept is present and segments all matching instances. While this presence-gated design improves concept-level prediction, its adversarial robustness remains unexplored. In this paper, we introduce Universal Concept Disruption (UCD), the first universal cross-concept adversarial attack tailored to SAM3 image segmentation. UCD learns a single bounded image perturbation from (image, noun-phrase) pairs and attacks SAM3 as an integrated concept-grounding system. It jointly disrupts the text-conditioned input path, maximizes divergence in prompt-shared visual features, suppresses the final presence-gated concept scores, and corrupts the spatial validity of retained masks through area collapse and clean-mask Dice disruption. Across SACo-Gold, LVIS, RefCOCO, PhraseCut, and OpenImages datasets, UCD consistently outperforms all baselines under a matched evaluation protocol, reducing average mask AP from 59.43 to 18.73 and average cgF1 from 50.32 to 20.49. The learned perturbation also transfers to SAM3.1 and to SAM3 video inference without re-optimization, while prompt ensembling, lightweight head fine-tuning, and temporal filtering provide limited recovery.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05983 — 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 2026-10-31T10:23:31.042Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).