AI Safety

GPT-4 is Judged More Human than Humans in Displaced and Inverted Turing Tests COLING 2025 Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining COLING 2025 Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion ICCV 2025 Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention ICCV 2025 GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation NAACL 2025 Granite Guardian: Comprehensive LLM Safeguarding NAACL 2025 Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience AAAI 2025 Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation EMNLP 2025 Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt. Generation for Enhanced LLM Content Moderation ACL 2025 Great Models Think Alike and this Undermines AI Oversight ICML 2025 Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending Against Poisoning Attacks AAAI 2025 G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems ACL 2025 Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation AAAI 2025 GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning ICML 2025 Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics ICML 2025 Guardians of Trust: Risks and Opportunities for LLMs in Mental Health ACL 2025 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents ACL 2025 Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints ACL 2025 h4rm3l: A Language for Composable Jailbreak Attack Synthesis ICLR 2025 HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025 HalLoc: Token-level Localization of Hallucinations for Vision Language Models CVPR 2025 HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead NAACL 2025 Hallucination Detection in LLMs Using Spectral Features of Attention Maps EMNLP 2025 Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training ACL 2025