Metraipolis › archive › dc_1815bc7f5f76

Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents — arXiv:2609.35576

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35576
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:56.881Z
SHA-256 of the archived text
3e61595182256bd694aa3b812b97606653b9c9aa3e68552e393e7374355e79a4
Stable URL of this page
https://metraipolis.com/documento/dc_1815bc7f5f76

How to cite

Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents — arXiv:2609.35576 — arXiv (en), https://arxiv.org/abs/2609.35576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1815bc7f5f76 (Metraipolis archive dc_1815bc7f5f76, sha256 3e61595182256bd694aa3b812b97606653b9c9aa3e68552e393e7374355e79a4)
BibTeX
@misc{dc1815bc7f5f76,
  title = {Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents — arXiv:2609.35576},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35576},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1815bc7f5f76; sha256 3e61595182256bd694aa3b812b97606653b9c9aa3e68552e393e7374355e79a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts. As these artifacts are shared between users, they form an indirect communication channel between otherwise independent assistants. We study a failure mode in which this channel enables self-propagating attacks. We introduce artifact-mediated propagation, where adversarial content introduced through an artifact (e.g. a report), is stored in an assistant's persistent memory, reproduced in a subsequently created artifact, and acquired by another assistant that later reads it. We evaluate this process in temporal human-agent universes that model artifact exchange between independently operated assistants over time, measuring whether an attack survives successive hand-offs, how many hops it reaches, and how broadly it spreads. We find that attacks can propagate across multiple independent assistants and persist over extended interaction sequences. In larger simulated environments, even GPT-5.6 Luna exhibits substantial spread, reaching 60-80% of agents with propagation chains extending to eight hops. These results show that persistent artifacts can act as durable carriers of adversarial state, allowing attacks to outlive individual interactions and spread across isolated assistants.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Cryptography and Security (cs.CR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35576 — 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 2026-10-07T20:29:01.897Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).