Metraipolis › archive › dc_339db077f292

Dynamic Watermarking and Action-Conditioned Latent Dynamics for Secure Vision-Based Controllers — arXiv:2611.07403

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07403
License (as archived): CC0-1.0
Archived: 2026-11-06T14:43:54.465Z
SHA-256 of the archived text: c1720b03b8e5390c9f3ceb627178c93db5df96b3264d27c07be5b5d56948cc58
Stable URL of this page: https://metraipolis.com/documento/dc_339db077f292

How to cite

Dynamic Watermarking and Action-Conditioned Latent Dynamics for Secure Vision-Based Controllers — arXiv:2611.07403 — arXiv (en), https://arxiv.org/abs/2611.07403 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_339db077f292 (Metraipolis archive dc_339db077f292, sha256 c1720b03b8e5390c9f3ceb627178c93db5df96b3264d27c07be5b5d56948cc58)

BibTeX

@misc{dc339db077f292,
  title = {Dynamic Watermarking and Action-Conditioned Latent Dynamics for Secure Vision-Based Controllers — arXiv:2611.07403},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07403},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_339db077f292; sha256 c1720b03b8e5390c9f3ceb627178c93db5df96b3264d27c07be5b5d56948cc58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07403. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Replay attacks are difficult to detect in vision-based control systems because previously recorded observations can remain plausible while the physical system follows a different trajectory. This paper develops an adaptive dynamic-watermarking framework for detecting replay attacks against vision-based controllers. A private Gaussian watermark is added to the nominal control input, and a control input-conditioned latent dynamics network (LDN) predicts the corresponding evolution in a compact latent space learned from image observations. Attack evidence is obtained from the discrepancy between the predicted latent response and the latent representation of the received image observation. A reinforcement learning policy adjusts the watermark covariance using the latent state and detector confidence, thereby balancing attack detectability, watermark energy, and control distortion. A Lagrangian penalty on task-specific safety costs is included during training to limit the adverse effect of the excitation. The framework is evaluated on a vision-guided UR5 manipulation task in which the robot reaches a target while avoiding a moving human arm under nominal and replay-attacked observations.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Cryptography and Security (cs.CR); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2611.07403 — 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 2026-11-06T14:21:12.535Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).