Metraipolis › archive › dc_afcaa0eb4deb

MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory — arXiv:2611.09721

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.09721
License (as archived): CC0-1.0
Archived: 2026-11-09T22:35:14.613Z
SHA-256 of the archived text: d6a39e0e197135e64294c7b9e38e57d4ae89f4fa766d8df116e06ce93dc367a3
Stable URL of this page: https://metraipolis.com/documento/dc_afcaa0eb4deb

How to cite

MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory — arXiv:2611.09721 — arXiv (en), https://arxiv.org/abs/2611.09721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_afcaa0eb4deb (Metraipolis archive dc_afcaa0eb4deb, sha256 d6a39e0e197135e64294c7b9e38e57d4ae89f4fa766d8df116e06ce93dc367a3)

BibTeX

@misc{dcafcaa0eb4deb,
  title = {MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory — arXiv:2611.09721},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09721},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_afcaa0eb4deb; sha256 d6a39e0e197135e64294c7b9e38e57d4ae89f4fa766d8df116e06ce93dc367a3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM agents benefit from using memory systems to improve performance on long-horizon, multi-session tasks. However, memory introduces a critical attack surface. Malicious instructions encountered in one session may be stored and propagated through memory before being retrieved and acted upon in later sessions. Because memory systems differ in how they process and retrieve information, the downstream effects of poisoning can vary significantly across systems. To quantify the effects of poisoning across different memory architectures, we introduce MemoryDojo, a benchmark for tracing the lifecycle of poisoned information through agent memory and measuring its influence on subsequent agent behavior. MemoryDojo is easily extensible, consists of 155 multi-session long-horizon trajectories covering four domains, and supports five different memory systems. Through our evaluation, we find that all memory systems are susceptible to memory poisoning, with substantial variation in downstream effects. We further propose a memory-aware poison optimization process that increases the poisoning efficacy, highlighting differences between memory architectures. We hope that MemoryDojo will support research on understanding and mitigating agentic memory risks.

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); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.09721 — 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 2026-11-09T22:30:47.341Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).