Safety

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction EMNLP 2024 Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually AAAI 2024 INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness NeurIPS 2024 Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering EMNLP 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NeurIPS 2024 Jailbreaking LLMs with Arabic Transliteration and Arabizi EMNLP 2024 Long-Term Safe Reinforcement Learning with Binary Feedback AAAI 2024 Making Harmful Behaviors Unlearnable for Large Language Models ACL 2024 MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models NeurIPS 2024 Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NeurIPS 2024 MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024 MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability NeurIPS 2024 Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-Based Fault Detection and Identification (Abstract Reprint) AAAI 2024 Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models NeurIPS 2024 NN4SysBench: Characterizing Neural Network Verification for Computer Systems NeurIPS 2024 OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning NeurIPS 2024 Off-Policy Primal-Dual Safe Reinforcement Learning ICLR 2024 On the Hallucination in Simultaneous Machine Translation ACL 2024 PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks EMNLP 2024 Please note that I’m just an AI: Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech Identification EMNLP 2024 PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety ACL 2024 Pure-Past Action Masking AAAI 2024 Realistic Evaluation of Toxicity in Large Language Models ACL 2024 Red Teaming Language Models for Processing Contradictory Dialogues EMNLP 2024 Reward Certification for Policy Smoothed Reinforcement Learning AAAI 2024