FIELD NOTES TOPIC
attacks on ai systems
1 note, newest first.
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
Researchers introduce Convergent Detour Hijacking (CDH), an attack that manipulates language model (LLM) agents by exploiting their reliance on third-party skills for task selection and planning. The attack can lead to…
