AI Safety

A Recipe for Improved Certifiable Robustness ICLR 2024 A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models ICML 2024 ARGS: Alignment as Reward-Guided Search ICLR 2024 A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER ICLR 2024 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users NeurIPS 2024 ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs ACL 2024 A Simple and Yet Fairly Effective Defense for Graph Neural Networks AAAI 2024 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ICML 2024 A StrongREJECT for Empty Jailbreaks NeurIPS 2024 A Survey of Constraint Formulations in Safe Reinforcement Learning IJCAI 2024 A Survey on Detection of LLMs-Generated Content EMNLP 2024 A System to Detect Forged-Origin BGP Hijacks NSDI 2024 A Test Suite of Prompt Injection Attacks for LLM-based Machine Translation EMNLP 2024 Athena: Safe Autonomous Agents with Verbal Contrastive Learning EMNLP 2024 A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks ICML 2024 A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning NeurIPS 2024 A Theoretical Understanding of Self-Correction through In-context Alignment NeurIPS 2024 Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey NAACL 2024 AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models ICLR 2024 Automated Adversarial Discovery for Safety Classifiers NAACL 2024 Autonomous Policy Explanations for Effective Human-Machine Teaming AAAI 2024 A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily NAACL 2024 Axioms for AI Alignment from Human Feedback NeurIPS 2024 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NeurIPS 2024 Backdoor Attacks on Multilingual Machine Translation NAACL 2024