most citedArchitecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

1 citations · 1 across the 12 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience

Zixuan Wang, Hao Li, Fengyu Gao +5

Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection a…