Metraipolis › archive › dc_4b6bf557db27
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems — arXiv:2609.27155
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27155
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:12:13.713Z
- SHA-256 of the archived text
73a488a97ba5b3b7617b530f6070c5c4b567a7199e291c454db5edb4ca63c459- Stable URL of this page
https://metraipolis.com/documento/dc_4b6bf557db27
How to cite
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems — arXiv:2609.27155 — arXiv (en), https://arxiv.org/abs/2609.27155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b6bf557db27 (Metraipolis archive dc_4b6bf557db27, sha256 73a488a97ba5b3b7617b530f6070c5c4b567a7199e291c454db5edb4ca63c459)
BibTeX
@misc{dc4b6bf557db27,
title = {The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems — arXiv:2609.27155},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27155},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b6bf557db27; sha256 73a488a97ba5b3b7617b530f6070c5c4b567a7199e291c454db5edb4ca63c459},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on users' behalf on the internet. However, the vulnerability of automated agents deployed on social media platforms (e.g., for managing a user's personal account) remains underexplored. Existing studies on agent poisoning typically assume that the adversary can expose poisoned content to the agent. Although such an attack is direct and effective, it is more easily detected and mitigated. In the context of social media platforms, this leaves open whether the recommendation system itself would surface such content to the agent in a more subtle manner. Through theoretical analysis, we show that the like-score mechanism used in OASIS can be exploited, and we characterize the conditions under which a multi-stage chain of poisoned posts can steer the agent's feed. Based on these insights, we further develop an algorithm that crafts realistic poisoned posts. Experiments support our theoretical findings and demonstrate the effectiveness of the proposed algorithm. Notably, by exploiting the like-score feedback loop, the attack causes the recommendation system to select poisoned posts even when their user-post similarity falls below the retrieval threshold. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.27155 — 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 2026-10-08T08:13:26.623Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).