评分 3.2 · 来源：cs.LG updates on arXiv.org · 发布于 2026-04-15
评分依据：Moderate AI relevance +practical(2)
arXiv:2510.05159v4 Announce Type: replace-cross Abstract: While finetuning AI agents on interaction data — such as web browsing or tool use — improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can effectively poison the data collection pipeline at multiple stages to embed hard-to-detect backdoors that, when triggered, cause unsafe or malicious behavior. We formalize three realistic threat models across…