conftrace_

guardrail system

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) character injection (1) code-switching attack (1) multilingual safety (1) word importance ranking (1) reward optimization (1) jailbreak detection (1) prompt injection (1) jailbreak attack (1) evasion attack (1)

Papers

Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems ACL 2025 X-Guard: Multilingual Guard Agent for Content Moderation ACL 2025