1
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
LLM防护盾反成攻击靶心：揭示基于大模型的agent安全护栏存在拒绝服务新漏洞
arXiv:2606.14517v1 Announce Type: cross Abstract: LLM-based guardrails have emerged as a highly effective defense against prompt injection and jailbre…