AI Safety

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations EMNLP 2024 MedBN: Robust Test-Time Adaptation against Malicious Test Samples CVPR 2024 Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration NeurIPS 2024 Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NeurIPS 2024 Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs NeurIPS 2024 Merging AI Incidents Research with Political Misinformation Research: Introducing the Political Deepfakes Incidents Database AAAI 2024 MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models NeurIPS 2024 Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems AAAI 2024 MICo: Preventative Detoxification of Large Language Models through Inhibition Control NAACL 2024 MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model CVPR 2024 Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NeurIPS 2024 Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination ACL 2024 Mitigating Emergent Robustness Degradation while Scaling Graph Learning ICLR 2024 Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation NeurIPS 2024 Mitigating robust overfitting via self-residual-calibration regularization (Abstract Reprint) IJCAI 2024 Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing ICLR 2024 MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models NeurIPS 2024 MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024 MMA-Diffusion: MultiModal Attack on Diffusion Models CVPR 2024 MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models CVPR 2024 Model Merging and Safety Alignment: One Bad Model Spoils the Bunch 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 Moral Foundations of Large Language Models EMNLP 2024 Moral Uncertainty and the Problem of Fanaticism AAAI 2024