← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Language Models Resist Alignment: Evidence From Data Compression ACL 2025
Representation Bending for Large Language Model Safety ACL 2025
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings ACL 2025
Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures ACL 2025
Arbiters of Ambivalence: Challenges of using LLMs in No-Consensus tasks ACL 2025
Exploiting Instruction-Following Retrievers for Malicious Information Retrieval ACL 2025
Removing Prompt-template Bias in Reinforcement Learning from Human Feedback ACL 2025
COVER: Context-Driven Over-Refusal Verification in LLMs ACL 2025
Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems ACL 2025
Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods EMNLP 2025
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs EMNLP 2025
ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocations EMNLP 2025
Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks CVPR 2025
Sugar-Coated Poison: Benign Generation Unlocks Jailbreaking EMNLP 2025
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis EMNLP 2025
Inverse Reinforcement Learning Meets Large Language Model Alignment ACL 2025
BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models CVPR 2025
Proxy Barrier: A Hidden Repeater Layer Defense Against System Prompt Leakage and Jailbreaking EMNLP 2025
MisinfoBench: A Multi-Dimensional Benchmark for Evaluating LLMs’ Resilience to Misinformation EMNLP 2025
Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization EMNLP 2025
Unraveling Misinformation Propagation in LLM Reasoning EMNLP 2025
Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences EMNLP 2025
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique EMNLP 2025
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders EMNLP 2025
Red-Teaming LLM Multi-Agent Systems via Communication Attacks ACL 2025