Metraipolis › archive › dc_ec356ddfb880
Defense Filters for Robust Learning of Partially Observed Dynamical Systems — arXiv:2610.21935
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21935
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:28:47.563Z
- SHA-256 of the archived text
715d49f6e7e5c65667ce93016039963543fd086bfdc3198a58aa1f0acb699b5d- Stable URL of this page
https://metraipolis.com/documento/dc_ec356ddfb880
How to cite
Defense Filters for Robust Learning of Partially Observed Dynamical Systems — arXiv:2610.21935 — arXiv (en), https://arxiv.org/abs/2610.21935 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec356ddfb880 (Metraipolis archive dc_ec356ddfb880, sha256 715d49f6e7e5c65667ce93016039963543fd086bfdc3198a58aa1f0acb699b5d)
BibTeX
@misc{dcec356ddfb880,
title = {Defense Filters for Robust Learning of Partially Observed Dynamical Systems — arXiv:2610.21935},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21935},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec356ddfb880; sha256 715d49f6e7e5c65667ce93016039963543fd086bfdc3198a58aa1f0acb699b5d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21935. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robust estimation of unknown system dynamics from partial observations under attack is a core challenge in learning for control, increasingly critical in multi-agent networks subject to adversarial data poisoning. Existing methods either require highly restrictive assumptions on the adversary or yield weak error bounds. In this paper, we consider identifying partially observed linear dynamical systems subject to adversarial attacks with an attack probability $p < 0.5$ at each time. We propose a defense-filtering framework in which a system designer leverages knowledge of the observation matrix to construct a defense filter satisfying full column rank and subspace separability conditions, which enables the evaluation of a single-attack scenario against observed data. Using this framework, we analyze the constrained $\ell_2$-norm estimator and establish finite-sample error bounds for recovering the Markov parameter matrix $G^*$. This is the first approach to provide provable system identification guarantees via a defense filter for partially observed systems subject to harsh attack environments where the attack probability approaches $0.5$. Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno). Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.21935 — 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 2026-10-16T08:49:47.934Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).