Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction

Reported by arXiv cs.CR (Haoran Bu, Yiting Shen, Litian Zhang, Ruihan Hu, Xi Zhang)

Summary by Cyber Security News30 Oct 2026, 05:00 CET

About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.38209

arXiv:2610.38209v1 Announce Type: new Abstract: LLM-based agents now share experiences on social platforms and remember new preferences to enhance their performance. However, existing memory systems contain a vulnerability in role-to-principal attribution that attackers can exploit.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.