AI Safety

AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025 AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025 Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems ACL 2025 Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents ICLR 2025 Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks ACL 2025 Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models EMNLP 2025 AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents EMNLP 2025 Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows EMNLP 2025 AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection ACL 2025 AIA: Autoregression-Based Injection Attacks Against Text2SQL Models AAAI 2025 AID: Adaptive Integration of Detectors for Safe AI with Language Models NAACL 2025 AI Governance and Lessons Learned as an AI Policy Advisor in the United States Senate AAAI 2025 AI-LieDar : Examine the Trade-off Between Utility and Truthfulness in LLM Agents NAACL 2025 AILS-NTUA at SemEval-2025 Task 3: Leveraging Large Language Models and Translation Strategies for Multilingual Hallucination Detection SemEval 2025 AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking SemEval 2025 AIM: Additional Image Guided Generation of Transferable Adversarial Attacks AAAI 2025 AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories ICLR 2025 AI Sandbagging: Language Models can Strategically Underperform on Evaluations ICLR 2025 AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology IJCNLP 2025 A Knapsack by Any Other Name: Presentation impacts LLM performance on NP-hard problems EMNLP 2025 Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study ACL 2025 Aligned LLMs Are Not Aligned Browser Agents ICLR 2025 Aligning Large Language Models for Faithful Integrity Against Opposing Argument AAAI 2025 Aligning to What? Limits to RLHF Based Alignment NAACL 2025 Aligning Visual Contrastive learning models via Preference Optimization ICLR 2025