AI Safety

Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models AAAI 2025 Attack on Prompt: Backdoor Attack in Prompt-Based Continual Learning AAAI 2025 Attacks by Content: Automated Fact-checking is an AI Security Issue EMNLP 2025 Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025 Attention Tracker: Detecting Prompt Injection Attacks in LLMs NAACL 2025 Attributive Reasoning for Hallucination Diagnosis of Large Language Models AAAI 2025 Audio Is the Achilles’ Heel: Red Teaming Audio Large Multimodal Models NAACL 2025 Auditing Political Bias in Text Generation by GPT-4 using Sociocultural and Demographic Personas: Case of Bengali Ethnolinguistic Communities AACL 2025 Auditing Prompt Caching in Language Model APIs ICML 2025 A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO ICML 2025 Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code COLING 2025 AUTE: Peer-Alignment and Self-Unlearning Boost Adversarial Robustness for Training Ensemble Models AAAI 2025 AutoAlign: Get Your LLM Aligned with Minimal Annotations ACL 2025 AutoCVSS: Assessing the Performance of LLMs for Automated Software Vulnerability Scoring EMNLP 2025 AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs ICLR 2025 Automated Progressive Red Teaming COLING 2025 Automated Red Teaming for Text-to-Image Models through Feedback-Guided Prompt Iteration with Vision-Language Models ICCV 2025 Automated Red Teaming with GOAT: the Generative Offensive Agent Tester ICML 2025 Automating Steering for Safe Multimodal Large Language Models EMNLP 2025 AutoPenBench: A Vulnerability Testing Benchmark for Generative Agents EMNLP 2025 Avoiding Catastrophe in Online Learning by Asking for Help ICML 2025 Axioms for AI Alignment from Human Feedback AAAI 2025 B4: A Black-Box Scrubbing Attack on LLM Watermarks NAACL 2025 Backdoor Attack on Propagation-based Rumor Detectors AAAI 2025 Backdoor Attacks on Neural Networks via One-Bit Flip ICCV 2025