Metraipolis › archive › dc_9bf2aa7ed4f5

SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval — arXiv:2610.22959

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22959
License (as archived)
CC0-1.0
Archived
2026-10-19T08:44:05.054Z
SHA-256 of the archived text
bdf7cc32939419c95c482508ac7bca6f8a4e10dfdcc0bae0a317906b035101c2
Stable URL of this page
https://metraipolis.com/documento/dc_9bf2aa7ed4f5

How to cite

SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval — arXiv:2610.22959 — arXiv (en), https://arxiv.org/abs/2610.22959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9bf2aa7ed4f5 (Metraipolis archive dc_9bf2aa7ed4f5, sha256 bdf7cc32939419c95c482508ac7bca6f8a4e10dfdcc0bae0a317906b035101c2)
BibTeX
@misc{dc9bf2aa7ed4f5,
  title = {SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval — arXiv:2610.22959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9bf2aa7ed4f5; sha256 bdf7cc32939419c95c482508ac7bca6f8a4e10dfdcc0bae0a317906b035101c2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized interactions. However, information collected from external sources can introduce security risks when untrusted claims (i.e., atomic statements) are later treated as authorized preferences, policies, or permissions. Existing defenses typically rely on content-based filtering or coarse-grained provenance tracking, which either fail to prevent unauthorized memory use or block legitimate information, sacrificing memory utility. To address these limitations, we propose SAFE-Mem, a fine-grained memory governance framework that improves security while preserving legitimate memory use. First, SAFE-Mem annotates each claim with three governance labels (i.e., kind, authority, and scope) to capture its provenance and permitted use. Second, governance-aware retrieval matches query requirements with claim permissions to block unauthorized influence while retaining legitimate information. Third, a governance-enabled memory graph connects source sentences, claims, and entities to support provenance tracking and efficient retrieval. Across four LLM backbones on MPBench and LoCoMo, SAFE-Mem attains the lowest attack success among defenses that retain legitimate memory, at least 77% below the strongest of them, and the highest answer accuracy of all evaluated defenses, improving it by up to 15%. The code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.22959 — 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 2026-10-19T08:39:24.900Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).