Frontier language models excel at complex tasks yet may prioritize protection over larger physical consequences in simple, urgent decisions. GPT-5.6 Sol, for example, moves a girl playing in shallow water before retrieving a submerged camera. We call this Protection Mode and study it with ProtectionBench: 285 prompts, 34 physical families, and nine models. At lowest effort, at least one of four responses prioritizes the subject on 34.74% of Sol prompts and over 83% of MiniMax M3 and Qwen3.5-27B prompts; none of four independent human raters does so. Controls show that choices usually track physical risk. We elicit both risks before requesting an action. Some models assess risk incorrectly; others state the correct ordering but still choose the subject. Qwen3.5-27B with thinking shows 100% correct risk ordering but 57.81% subject choice among eligible conversations on eight selected scenes. Attention audits find no stable reduction in attention to relevant facts; removing the stated risk direction reduces object-first choice in dots3-note-prev but not detectably in Qwen3.5-27B. Adding a general "people or animals before property" rule increases subject choice by 19-38 percentage points, whereas factual reminders favor the object by 0.7-5.2 points. Removing naturally generated versions of that rule lowers subject choice by 10-15 points. We also examine whether post-training introduces this pattern. Base models already show Protection Mode; post-training changes justifications more than choices.
Visual Distraction Undermines Moral Reasoning in Vision-Language Models
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);School of Psychological and Cognitive Sciences, Peking University(北京大学心理与认知科学学院);Yuanpei College, Peking University(北京大学元培学院);Department of Psychology, Sun Yat-sen University(中山大学心理学系);State Key Lab of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室);Beijing Key Laboratory of Behavior and Mental Health, Peking University(北京大学行为与心理健康北京市重点实验室)
A Privacy by Design Framework for Large Language Model-Based Applications for Children
Computer Engineering Carleton University Ottawa, Canada(计算机工程学院卡罗伦大学加拿大);School of Information Technology Carleton University Ottawa, Canada(信息科技学院卡罗伦大学加拿大);Legal Studies Carleton University Ottawa, Canada(法律研究学院卡罗伦大学加拿大)
Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs
College of Computing and Information Science(计算与信息科学学院);Siebel School of Computing and Data Science(计算与数据科学学院);Cornell University(康奈尔大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);New York, USA(美国纽约);Champaign, Illinois, USA(美国伊利诺伊州香槟)
General-purpose AI models can generate actionable knowledge on agroecological crop protection
Chrysalis Consulting(Chrysalis咨询公司);Institute for Plant Protection, China Academy of Agricultural Sciences(中国农业科学院植物保护研究所);School of the Environment, University of Queensland(昆士兰大学环境学院)
Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
Centre for Frontier AI Research (CFAR)(前沿人工智能研究所在);Institute of High Performance Computing (IHPC)(高性能计算研究所);Agency for Science, Technology and Research(科技研究局);D-ITET;ETH Zurich(苏黎世联邦理工学院);CCDS, Nanyang Technological University(南洋理工大学CCDS)
Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing
East China Normal University(华东师范大学);Guangxi Normal University(广西师范大学);Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong(香港中文大学深圳大数据研究院)