Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration AAAI 2024

Towards Trustworthy Deep Learning AAAI 2024

Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World IJCAI 2024

Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspective IJCAI 2024

Mitigating robust overfitting via self-residual-calibration regularization (Abstract Reprint) IJCAI 2024

When Your AI Becomes a Target: AI Security Incidents and Best Practices AAAI 2024

Alignment for Honesty NIPS 2024

Safety of Multimodal Large Language Models on Images and Text IJCAI 2024

STAR: SocioTechnical Approach to Red Teaming Language Models EMNLP 2024

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs NIPS 2024

Fight Back Against Jailbreaking via Prompt Adversarial Tuning NIPS 2024

Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models NIPS 2024

Do LLMs Know to Respect Copyright Notice? EMNLP 2024

Bounded robustness in reinforcement learning via lexicographic objectives L4DC 2024

Validating the eBPF Verifier via State Embedding OSDI 2024

CriticEval: Evaluating Large-scale Language Model as Critic NIPS 2024

Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models EMNLP 2024

Defending Jailbreak Prompts via In-Context Adversarial Game EMNLP 2024

Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models EMNLP 2024

Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse EMNLP 2024

Jailbreaking LLMs with Arabic Transliteration and Arabizi EMNLP 2024

Moral Uncertainty and the Problem of Fanaticism AAAI 2024

On the Relationship between Truth and Political Bias in Language Models EMNLP 2024

Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution EMNLP 2024

Fair Secretaries with Unfair Predictions NIPS 2024