Skip to content
conftrace_

harmful keyword

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

security-aware classification (1) prompt classification (1) prompt security (1) jailbreak detection (1) attack detection (1) jailbreak attack (1) query-based summarization (1) llm defense (1) harmful content (1) text summarization (1)

Papers

Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025