Metraipolis › archive › dc_3863be50f331

Visual Tripwires: Anticipating Failure in Deep Vision Systems — arXiv:2609.28099

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.28099
License (as archived): CC0-1.0
Archived: 2026-10-08T10:58:16.363Z
SHA-256 of the archived text: 6bea2a6dff6df8df5de17529ebc7512a4339f20b826d5d5a6a7021aaa0db4e2b
Stable URL of this page: https://metraipolis.com/documento/dc_3863be50f331

How to cite

Visual Tripwires: Anticipating Failure in Deep Vision Systems — arXiv:2609.28099 — arXiv (en), https://arxiv.org/abs/2609.28099 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3863be50f331 (Metraipolis archive dc_3863be50f331, sha256 6bea2a6dff6df8df5de17529ebc7512a4339f20b826d5d5a6a7021aaa0db4e2b)

BibTeX

@misc{dc3863be50f331,
  title = {Visual Tripwires: Anticipating Failure in Deep Vision Systems — arXiv:2609.28099},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28099},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3863be50f331; sha256 6bea2a6dff6df8df5de17529ebc7512a4339f20b826d5d5a6a7021aaa0db4e2b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28099. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep vision systems remain vulnerable to corruption, occlusion, and distribution shift despite strong benchmark performance. Existing reliability methods typically evaluate uncertainty at individual time steps and do not explicitly model how a system progresses toward failure. We introduce Visual Tripwires, a predictive reliability framework that uses temporal instability in model behaviour to anticipate impending failure. Our central hypothesis is that predictive degradation develops progressively through measurable changes in latent representations, prediction trajectories, and attention structure. Visual Tripwires captures these changes using representation drift, prediction oscillation, trajectory curvature, and attention entropy. A lightweight tripwire predictor aggregates these signals over a temporal window to estimate the probability of failure within a future prediction horizon. Experiments across multiple datasets, architectures, and progressive perturbation settings show that the proposed instability signals emerge before predictive degradation and provide earlier and more accurate failure warnings than conventional uncertainty estimation methods. These results demonstrate that temporal instability contains useful information about future model reliability and provides a practical basis for early warning in deep vision systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.28099 — 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 2026-10-08T10:06:16.837Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).