AI Safety

Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position AAAI 2026 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 Yours or Mine? Overwriting Attacks Against Neural Audio Watermarking AAAI 2026 Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models EACL 2026 Zero-Shot Detection of LLM-Generated Text using Temperature Sensitivity ACL 2026 R^2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning ICLR 2025 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning ACL 2025 A Benchmark for Semantic Sensitive Information in LLMs Outputs ICLR 2025 A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety ICLR 2025 ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning ICML 2025 ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awareness ACL 2025 A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment ICML 2025 A Closer Look at Generalized BH Algorithm for Out-of-Distribution Detection ICML 2025 A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient NAACL 2025 A Comprehensive Evaluation of Cognitive Biases in LLMs NAACL 2025 A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics IJCAI 2025 Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks ICLR 2025 Activation Space Interventions Can Be Transferred Between Large Language Models ICML 2025 Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model ACML 2025 Activation Subspaces for Out-of-Distribution Detection ICCV 2025 Active Fourier Auditor for Estimating Distributional Properties of ML Models AAAI 2025 Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats ICLR 2025 Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing ACL 2025 Adaptive Localization of Knowledge Negation for Continual LLM Unlearning ICML 2025 AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025