Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents

Reported by arXiv cs.CR (Wonjun Lee, Vaidehi Patil, Zaid Khan, Yue Zhang, Hyunji Lee, Suhyun Kim, Mohit Bansal)

Summary by Cyber Security News20 Oct 2026, 06:00 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/2610.24379

arXiv:2610.24379v1 Announce Type: new Abstract: Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents, whether dormant poisoning extends to harmful agent actions and multimodal settings remains unclear.

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.