Metraipolis › archive › dc_c35e256feaeb

Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation — arXiv:2611.00923

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00923
License (as archived): CC0-1.0
Archived: 2026-11-03T10:35:37.303Z
SHA-256 of the archived text: fb87356d232eaddca4fc23b90a9664017f32af54a7538aff40ced227744c353c
Stable URL of this page: https://metraipolis.com/documento/dc_c35e256feaeb

How to cite

Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation — arXiv:2611.00923 — arXiv (en), https://arxiv.org/abs/2611.00923 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c35e256feaeb (Metraipolis archive dc_c35e256feaeb, sha256 fb87356d232eaddca4fc23b90a9664017f32af54a7538aff40ced227744c353c)

BibTeX

@misc{dcc35e256feaeb,
  title = {Illusion: Safeguarding Topology Confidentiality in LLM Multi-Agent Systems via Behavior-Preserving Obfuscation — arXiv:2611.00923},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00923},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c35e256feaeb; sha256 fb87356d232eaddca4fc23b90a9664017f32af54a7538aff40ced227744c353c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00923. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The communication topology of Large Language Model Multi-Agent Systems (LLM-MASs) governs how information propagates among agents and encodes critical domain knowledge and expert workflow design. It is valuable intellectual property and plays a decisive role in system utility and safety, yet remains vulnerable to inference attacks that stealthily reconstruct it from agent outputs. Existing defenses detect or mitigate such attacks but do not proactively conceal the topology itself. We propose \textit{Illusion}, a proactive topology obfuscation defense for LLM-MAS. \textit{Illusion} injects fake edges and fake messages to present attackers with a deceptive topology, while selecting low-impact candidates that preserve output-distribution equivalence and task-accuracy non-inferiority. The resulting fake edges are designed to be indistinguishable from genuine messages under black-box observation. Extensive experiments show that \textit{Illusion} reduces edge-level F1 from over 0.87 to 0.62 and graph similarity from over 0.94 to 0.71. It also largely preserves output distributions and task performance, and its fake edges resist both similarity-based and LLM-judge filtering, even under adaptive pruning.

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/2611.00923 — 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 2026-11-03T10:29:48.730Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).