AI Safety

Differentially Private Federated Learning with Time-Adaptive Privacy Spending ICLR 2025 Differentially Private Steering for Large Language Model Alignment ICLR 2025 DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak EMNLP 2025 DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events? EMNLP 2025 Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy ICCV 2025 Dissecting Adversarial Robustness of Multimodal LM Agents ICLR 2025 DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion ICCV 2025 Distraction is All You Need for Multimodal Large Language Model Jailbreaking CVPR 2025 Distributional Surgery for Language Model Activations EMNLP 2025 DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints AAAI 2025 Diversity Helps Jailbreak Large Language Models NAACL 2025 Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models ICLR 2025 Do as We Do, Not as You Think: the Conformity of Large Language Models ICLR 2025 Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking? ACL 2025 Does GPT Really Get It? A Hierarchical Scale to Quantify Human and AI’s Understanding of Algorithms AAAI 2025 Does Knowing More Make You Easier to Trick? Adversarial Robustness of Multi-Target Regression AAAI 2025 Does Refusal Training in LLMs Generalize to the Past Tense? ICLR 2025 Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts? ICLR 2025 Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs EMNLP 2025 Do LLMs Behave as Claimed? Investigating How LLMs Follow Their Own Claims using Counterfactual Questions EMNLP 2025 Do LLMs estimate uncertainty well in instruction-following? ICLR 2025 Do LLMs have Consistent Values? ICLR 2025 Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models COLING 2025 Do not Abstain! Identify and Solve the Uncertainty ACL 2025 Don’t Say No: Jailbreaking LLM by Suppressing Refusal ACL 2025