AI Safety

Safety of Multimodal Large Language Models on Images and Text IJCAI 2024 Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions ICLR 2024 Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? NeurIPS 2024 SafeWorld: Geo-Diverse Safety Alignment NeurIPS 2024 SALMON: Self-Alignment with Instructable Reward Models ICLR 2024 Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems AISTATS 2024 Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs NAACL 2024 SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP ICML 2024 SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales EMNLP 2024 Scalable AI Safety via Doubly-Efficient Debate ICML 2024 Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes NeurIPS 2024 Scalable Safe Policy Improvement for Factored Multi-Agent MDPs ICML 2024 Scaling the Convex Barrier with Sparse Dual Algorithms JMLR 2024 Scanning Trojaned Models Using Out-of-Distribution Samples NeurIPS 2024 Secret Collusion among AI Agents: Multi-Agent Deception via Steganography NeurIPS 2024 SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures Interspeech 2024 SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases EMNLP 2024 Secure Your Model: An Effective Key Prompt Protection Mechanism for Large Language Models NAACL 2024 Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks EMNLP 2024 SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly AAAI 2024 SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions NeurIPS 2024 Segmenting Watermarked Texts From Language Models NeurIPS 2024 Selective Generation for Controllable Language Models NeurIPS 2024 Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation ACL 2024 Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation ICLR 2024