AI Safety

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction EMNLP 2025 Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs ACL 2025 Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset NAACL 2025 Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models ACL 2025 Beyond Words: Multilingual and Multimodal Red Teaming of MLLMs ACL 2025 Bias Amplification: Large Language Models as Increasingly Biased Media IJCNLP 2025 Biased LLMs can Influence Political Decision-Making ACL 2025 Bias in the Mirror : Are LLMs opinions robust to their own adversarial attacks ACL 2025 Binary Classifier Optimization for Large Language Model Alignment ACL 2025 Black-Box Adversarial Attacks on LLM-Based Code Completion ICML 2025 Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models CVPR 2025 Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring ACL 2025 BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks ICLR 2025 BlueToad at SemEval-2025 Task 3: Using Question-Answering-Based Language Models to Extract Hallucinations from Machine-Generated Text SemEval 2025 BOND: Aligning LLMs with Best-of-N Distillation ICLR 2025 Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation ICLR 2025 BotSim: LLM-Powered Malicious Social Botnet Simulation AAAI 2025 Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time ICML 2025 Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses ICLR 2025 Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification EMNLP 2025 Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders EMNLP 2025 Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature AAAI 2025 Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In NAACL 2025 Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space ACL 2025 Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks EMNLP 2025