Metraipolis › archive › dc_cbb51a2e8ed7

Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity — arXiv:2608.03272

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03272
License (as archived)
CC0-1.0
Archived
2026-10-31T12:14:38.773Z
SHA-256 of the archived text
0a74dbd736a7fc68fde967525860d83b2027040eb98cc9eb7c5739ad6d296b23
Stable URL of this page
https://metraipolis.com/documento/dc_cbb51a2e8ed7

How to cite

Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity — arXiv:2608.03272 — arXiv (en), https://arxiv.org/abs/2608.03272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbb51a2e8ed7 (Metraipolis archive dc_cbb51a2e8ed7, sha256 0a74dbd736a7fc68fde967525860d83b2027040eb98cc9eb7c5739ad6d296b23)
BibTeX
@misc{dccbb51a2e8ed7,
  title = {Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity — arXiv:2608.03272},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03272},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbb51a2e8ed7; sha256 0a74dbd736a7fc68fde967525860d83b2027040eb98cc9eb7c5739ad6d296b23},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent collaborative filtering (CF) systems coordinate autonomous LLM-powered user and item agents through natural-language interaction to refine preferences and generate recommendations. These systems inherit vulnerabilities from both their data-driven nature and their multi-agent interactions, which manifest in distinct ways. Understanding how connectivity modulates vulnerability in these systems could facilitate the development of more robust recommendation pipelines. In this work, we adapt attacks and defenses from the general multi-agent systems (MAS) literature to the agent-based CF setting, evaluating them under systematically varied connectivity in the AgentCF framework, where CF connectivity is characterized along two axes: (i) candidate count (the number of item candidates per turn per user, measuring user-side interaction density) and (ii) catalog concentration (the degree of item catalog overlap across users). Our contributions include: (1) Adaptation: we reproduce MAS-inspired attacks and defenses in the agentic CF domain, confirming partial transferability of original observations. (2) Characterization: we characterize how the two aspects of connectivity shape attack and defense outcomes, revealing role asymmetries between user and item agents, non-monotonic temporal dynamics in attack efficacy, and divergent patterns across dissemination and extraction attack goals. Additionally, as an exploratory extension, we assess the applicability of epidemic-inspired static metrics in ranking CF configurations by expected attack outcome, potentially enabling cost-efficient robustness assessment. Implementation is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.MA).
Categorie arXiv: Information Retrieval (cs.IR) ; Cryptography and Security (cs.CR); Multiagent Systems (cs.MA); Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2608.03272 — 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 2026-10-31T12:05:27.221Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).