Metraipolis › archive › dc_8b151d11ef73
Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems — arXiv:2610.05689
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05689
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:18.459Z
- SHA-256 of the archived text
82178d56debe9d589861e98c328b7d36e4c0529e84a25b799efee7f7a3150d8f- Stable URL of this page
https://metraipolis.com/documento/dc_8b151d11ef73
How to cite
Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems — arXiv:2610.05689 — arXiv, https://arxiv.org/abs/2610.05689 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b151d11ef73 (Metraipolis archive dc_8b151d11ef73, sha256 82178d56debe9d589861e98c328b7d36e4c0529e84a25b799efee7f7a3150d8f)
BibTeX
@misc{dc8b151d11ef73,
title = {Toward AI Trustworthiness: Finding Analytically Proven Forward-Invariant Sets for AI-Controlled Systems — arXiv:2610.05689},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05689},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b151d11ef73; sha256 82178d56debe9d589861e98c328b7d36e4c0529e84a25b799efee7f7a3150d8f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05689. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural-network (NN) controllers are increasingly used in nonlinear control systems, but their highly nonlinear behavior makes them difficult to explain and verify, raising trustworthiness concerns in safety- and mission-critical applications. A key step toward certifiable trustworthiness is to find a Forward-Invariant Set (FIS): a state-space region such that any trajectory starting inside remains inside. If the FIS excludes unsafe states, safety can be guaranteed for initial states within it. Finding an analytically proven FIS for a given AI-controlled system with a fixed controller is difficult. We propose a framework that uses an Invertible Neural Network (INN) to transform the original state space into a latent space where a regular-shaped FIS is more likely to exist. We train the INN so that a preferred hyper-rectangular candidate becomes invariant in the latent space, then formally verify it. We prove that, whenever verification succeeds, both the latent-space candidate and its inverse-transformed counterpart in the original state space are analytically proven FISs. We evaluate the approach on 45 AI-controlled systems across three representative control testbeds. Our method finds certified FISs for all 45 systems, whereas an adapted state-of-the-art baseline finds none. It is also faster on 40 of the 45 systems, and the centers of the resulting FISs roughly match domain-expert preferences. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.05689 — 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 2026-10-06T05:24:05.622Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).