Skip to content
conftrace_

prompt security

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) jailbreak detection (3) adversarial attack (2) ai safety (2) jailbreak prevention (1) in-context adversarial game (1) harmful keyword (1) security-aware classification (1) prompt classification (1) jailbreak prompt (1)

Papers

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security AAAI 2026 LLM Jailbreak Detection for (Almost) Free! EMNLP 2025 Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025 A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily NAACL 2024 Defending Jailbreak Prompts via In-Context Adversarial Game EMNLP 2024 GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher ICLR 2024 GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis ACL 2024