Metraipolis › archive › dc_92231cd85698

The Limits of Information-Flow Control Enforcement for Agentic Systems — arXiv:2611.10395

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10395
License (as archived)
CC0-1.0
Archived
2026-11-10T18:42:26.275Z
SHA-256 of the archived text
bf3bbef3fb90061653df7c3d4518d7471beae8d5d451a9ecba9456e2472694bb
Stable URL of this page
https://metraipolis.com/documento/dc_92231cd85698

How to cite

The Limits of Information-Flow Control Enforcement for Agentic Systems — arXiv:2611.10395 — arXiv (en), https://arxiv.org/abs/2611.10395 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_92231cd85698 (Metraipolis archive dc_92231cd85698, sha256 bf3bbef3fb90061653df7c3d4518d7471beae8d5d451a9ecba9456e2472694bb)
BibTeX
@misc{dc92231cd85698,
  title = {The Limits of Information-Flow Control Enforcement for Agentic Systems — arXiv:2611.10395},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10395},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_92231cd85698; sha256 bf3bbef3fb90061653df7c3d4518d7471beae8d5d451a9ecba9456e2472694bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10395. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Information-flow control (IFC) is a promising approach to enforce policy in agentic AI systems. However, IFC suffers from label creep, a phenomenon where monotonically increasing security labels propagate through a system and progressively limit its utility. Label creep in agentic AI systems can be mitigated using two major strategies: (1) improved system design and (2) label declassification. In this paper, we characterize how far system design alone can mitigate label creep in agentic systems. Specifically, we measure how system topology, scale, and agent composition affect utility loss and security enforcement cost proxies for conservative IFC enforcement in a stateful agentic system simulator. We develop a pipeline to systematically vary these features and measure their impacts on label propagation. Our results demonstrate strong associations between structural graph features and our IFC utility loss metric (up to a Spearman correlation $|\rho|$ of $0.96$) and show that system size and tool allocation substantially affect how labels propagate. These findings identify design choices to reduce IFC utility loss, but they also demonstrate that system design alone cannot fully prevent utility loss due to monotonic label propagation. This motivates the development of label declassification mechanisms that aid these design choices and diminish IFC utility cost.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.10395 — 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 2026-11-10T18:37:37.585Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).