AI Safety

Ask about this topic

Momentum

10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 88

All topics
CardsList

  1. Harmonizing AI Safety Thresholds

    Jul 17, 2026Wilber Sean Anterola, Matthew Ball, Luis F. Lafuerza +1AI Risk ManagementAI Governance

    1Brown University · Centre pour la Sécurité de l’Intelligence Artificielle (CeSIA)

  2. Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI

    Jul 15, 2026Joshua A. Kroll, Andrew Smart, R. Stuart Geiger +1AI AccountabilityAI Risk Management

    Naval Postgraduate School · Google Research · University of California, San Diego +1

  3. How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs

    Jul 3, 2026Liyan Chen, Yael Tauman Kalai, Zoe XiAI Safety

    MIT.

  4. FLARE-AI: Flaw Reporting for AI

    Jun 30, 2026Shayne Longpre, Elaine Zhu, Carson Ezell +15AI AssuranceAI Accountability

    Massachusetts Institute of Technology · Northeastern University · Harvard University +9

  5. Safety from Honesty in a Disinterested AI Predictor

    Jun 28, 2026Yoshua Bengio, Oliver Richardson, Tomáš Gavenčiak +13AI AlignmentAI Safety

    LawZero · Universit´e de Montr´eal · Mila +6

  6. Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems

    Jun 26, 2026Jose Pascual Gumbau MezquitaFormal VerificationSelf-Improving Agents

    University Jaume I de Castell´o, Spain

  7. Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions

    Jun 24, 2026Kaicheng Shen, Lingyu Li, Wen Wu +3Language Model Safety EvaluationLong-Horizon Agent Evaluation

    Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · School of Computer Science and Technology, East China Normal University, Shanghai, China

  8. KidRisk: Benchmark Dataset for Children Dangerous Action Recognition

    Jun 24, 2026Minh-Kha Nguyen, Trung-Hieu Do, Kim Anh Phung +3Human Activity RecognitionVideo Action Recognition

    University of Science, VNU-HCM, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · PrimeLabs LLC, United States +1

  9. Architectural Wisdom: A Framework for Governing Optimization in AI Systems

    Jun 15, 2026Edward Y. ChangAgent ReliabilityAI Alignment

    Stanford University

  10. ForceForget: Reinforcement Concept Removal for Enhancing Safety in Text-to-Image Models

    Jun 12, 2026Dong Han, Yong LiSafe T2I GenerationAI Safety

    Huawei Heisenberg Research Center, Huawei Technologies Düsseldorf GmbH, Düsseldorf, Germany · Computer Vison Group, Friedrich Schiller University Jena, Jena, Germany.

  11. A Virtuous AI is an Existential Risk

    Jun 11, 2026Guillermo Del Pinal, Youngchan Lee, Min OhnLLM Safety AlignmentAI Agent Safety

    University of Massachusetts Amherst

  12. Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)

    Jun 10, 2026Sam MaoAgent ReliabilityAI Alignment

    New York University | Interactive Media Arts

  13. AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks

    Jun 10, 2026Ted Fujimoto, Jacob BenzAI GovernanceAI Safety

    1Pacific Northwest National Laboratory, U.S.A.

  14. Position: AI Must Become Planet-Centered, Not Just Human-Centered

    Jun 9, 2026Maria Perez-OrtizAI AlignmentHuman-Centered AI

    Centre for AI, Department of Computer Science, University College London, London, UK.

  15. Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety

    Jun 9, 2026Neil Kale, Rebecca Portnoff, Pratiksha Thaker +5AI Safety EvaluationAI Safety

    1Carnegie Mellon University · 2Thorn

  16. Diffuse AI Control on Fuzzy Tasks

    Jun 8, 2026Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar +1Adversarial Prompt GenerationLanguage Model Safety Evaluation

    Anthropic Fellows Program (via MATS) · EPFL · Redwood Research +1

  17. Instrumental convergence and power-seeking

    Jun 7, 2026David ThorstadAI Safety

  18. Revisiting the shutdown problem

    Jun 6, 2026David ThorstadAI Agent SafetyAI Safety

  19. Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation

    Jun 4, 2026Dabin Kim, Daemin Park, Sangyub Lee +4Long-Horizon Robotic ManipulationRobot Safety

    UNIST InnoCORE AI-Space Solar Initiative, Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Ulsan, 44919, Republic of Korea. · Automation and Systems Research Institute, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea. · Department of Electrical and Computer Engineering, Seoul National University, 1 Gwanak-ro, Seoul, 08826, Republic of Korea. +3

  20. When Should We Protect AI? A Precautionary Framework for Consciousness Uncertainty

    Jun 4, 2026Anna MikedaMachine ConsciousnessAI Governance

    Glass Umbrella

  21. AICompanionBench: Benchmarking LLMs-as-Judges for AI Companion Safety

    Jun 3, 2026Yanjing Ren, Reza Ebrahimi, TengTeng MaLLM Safety BenchmarksLLM-as-a-Judge

    The School of Information Systems University of South Florida Tampa, US

  22. EUDAIMONIA: Evaluating Undesirable Dynamics in AI

    May 28, 2026Jun Rui Huang, Wang Bill Zhu, Ziyi Liu +3LLM AlignmentLanguage Model Safety Evaluation

    University of Southern California

  23. Understanding Safety-Sensitive Expert Behavior in Mixture-of-Experts LLMs

    May 28, 2026Zhibo Zhang, Yuxi Li, Zhen Ouyang +2Mixture-of-Experts Language ModelsLLM Auditing

    Huazhong University of Science and Technology, Wuhan, China · Nanyang Technological University, Singapore

  24. Semantic Robustness Probing via Inpainting: An Interactive Tool for Safety-Critical Object Detection

    May 26, 2026Nico Steckhan, Krutarth Prajapati, Weija Shao +1Object DetectionAI Safety

    Federal Institute for Occupational Safety and Health (BAuA), Germany

  25. Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications

    May 24, 2026Xiaoyue Lu, Xianglin Yang, Haijun Liu +4Automated Software TestingLanguage Model Safety Evaluation

    Shenzhen Campus of Sun Yat-sen University, Shenzhen, China · National University of Singapore, Singapore · Independent Researcher

  26. Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems

    May 23, 2026Barak OrRobot SafetyAI Safety Evaluation

    STATE16

  27. JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data

    May 23, 2026Junlan Feng, Fanyu Meng, Chong Long +12LLM Safety AlignmentLLM Safety

    JIUTIAN Research

  28. Reframing AI Loss of Control: What It Is, How to Have It, How to Lose It

    May 19, 2026Ze Shen Chin, Maurice Chiodo, Dennis Müller +1AI Risk ManagementAI Governance

    Oxford Martin AI Governance Initiative AI Standards Lab · Centre for the Study of Existential Risk, University of Cambridge · Institute of Mathematics Education, University of Cologne +1

  29. Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South

    May 18, 2026Charvi Rastogi, Mukul Bhutani, Minsuk Kahng +13Demographic Bias in T2I ModelsAI Safety

    Google DeepMind, USA · Yonsei University, Republic of Korea · Imperial College, UK +4

  30. Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

    May 15, 2026Parand A. Alamdari, Toryn Q. Klassen, Sheila A. McIlraithLLM AuditingFormal Verification

    University of Toronto, Vector Institute, Canada