AI Safety

Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience EMNLP 2025 STAR: Self-Automated Back-Querying for Production Data Generation IJCNLP 2025 Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models CVPR 2025 Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring NAACL 2025 Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks CVPR 2025 Stepwise Reasoning Disruption Attack of LLMs ACL 2025 STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models CVPR 2025 Stereotype or Personalization? User Identity Biases Chatbot Recommendations ACL 2025 Stimulate the Critical Thinking of LLMs via Debiasing Discussion EMNLP 2025 STLC-KG:A Social Text Steganalysis Method Combining Large-Scale Language Models and Common-Sense Knowledge Graphs AAAI 2025 StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025 Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense AAAI 2025 Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation ICML 2025 Strong Empowered and Aligned Weak Mastered Annotation for Weak-to-Strong Generalization AAAI 2025 Stronger Universal and Transferable Attacks by Suppressing Refusals NAACL 2025 Strong Preferences Affect the Robustness of Preference Models and Value Alignment ICLR 2025 Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework EMNLP 2025 SUA: Stealthy Multimodal Large Language Model Unlearning Attack EMNLP 2025 Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making EMNLP 2025 sudoLLM: On Multi-role Alignment of Language Models EMNLP 2025 SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment ACL 2025 sudo rm -rf agentic_security ACL 2025 Sugar-Coated Poison: Benign Generation Unlocks Jailbreaking EMNLP 2025 Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings ICML 2025 Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025