llm safety

Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering EMNLP 2025 Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025 LLM Safety for Children NAACL 2025 LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts ACL 2025 MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol EMNLP 2025 One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs ICLR 2025 On Localizing and Deleting Toxic Memories in Large Language Models NAACL 2025 PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization ACL 2025 RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process NAACL 2025 Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025 Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025 SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025 SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety AAAI 2025 SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025 SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage ACL 2025 SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage ACL 2025 SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters NAACL 2025 SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains ACL 2025 Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM Aggression ACL 2025 Stepwise Reasoning Disruption Attack of LLMs ACL 2025 Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making EMNLP 2025 ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocations EMNLP 2025 Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languages EMNLP 2025 TrapDoc: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents EMNLP 2025 What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs ACL 2025