Back to papers
August 12, 2026cs.CRcs.AI

Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents

Junliang Liu, Ruoyu Li, Wenxin Tang, Jingyu Xiao, Zhenyu Liu, Jingheng Xu, Laizhong Cui
Read on arXivDownload PDF
Categories

cs.CR, cs.AI