conftrace_

jailbreak prevention

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) adversarial attack (3) ai safety (3) jailbreak defense (2) adversarial defense (2) safety-utility trade-off (1) policy adherence (1) prompt security (1) safety generalization (1) harmfulness detection (1)

Papers

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security AAAI 2026 Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models ACL 2026 Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing ACL 2025 Effective Red-Teaming of Policy-Adherent Agents EMNLP 2025 MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025