SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
SoK: 深度强化学习在网络安全中的陷阱
Shae McFadden, Myles Foley, Elizabeth Bates, Ilias Tsingenopoulos, Sanyam Vyas, Vasilios Mavroudis, Chris Hicks, Fabio Pierazzi
机构
*
King’s College London(伦敦国王学院)
;
The Alan Turing Institute(艾伦·图灵研究所)
;
University College London(伦敦大学学院)
;
Cardiff University(卡迪夫大学)
;
KU Leuven(鲁汶大学)
;
Devotion AI Labs(Devotion AI 实验室)
Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series
全球海上风电基础设施:基于密集Sentinel-1时间序列的部署与运行动态
Thorsten Hoeser, Felix Bachofer, Claudia Kuenzer
机构
*
Earth Observation Center (EOC), German Aerospace Center (DLR)(地球观测中心(EOC),德国航空航天中心(DLR))
;
Institute for Geography and Geology, University of Wuerzburg(地理与地质研究所,乌尔姆大学)
Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?
受神经启发的多模态视觉-语言模型对成员推断隐私泄露是否具有弹性?
David Amebley, Sayanton Dibbo
机构
*
The University of Alabama(阿拉巴马大学)
;
Alabama Center for the Advancement of AI(阿拉巴马人工智能 advancement 中心)
;
Trustworthy AI Lab(可信人工智能实验室)
;
Department of Computer Science, The University of Alabama(计算机科学系)
机构
*
Institute of Operations Research and Analytics National University of Singapore(运营研究与分析研究所,新加坡国立大学)
;
Department of Mathematics Department of Electrical and Computer Engineering Institute of Operations Research and Analytics National University of Singapore(数学系电子与计算机工程系运营研究与分析研究所,新加坡国立大学)
;
Department of Mathematics National University of Singapore(数学系新加坡国立大学)
Commentsv2: Minor numerical corrections for Table V. 16 pages, 14 figures, 7 tables. Extended version of paper accepted to 2026 IEEE Intelligent Vehicles Symposium (IV 2026). ScenicRules benchmark available at https://github.com/BerkeleyLearnVerify/ScenicRules
CommentsRevised version of "The Politics of (No) Compromise: Information Acquisition, Policy Discretion, and Reputation" (arXiv:2111.00522). Same model and core results: constrained delegation restores a career-concerned agent's incentive to acquire information by eliminating the action that serves as the uninformed agent's safe harbor. Retitled "Constraining to Motivate."
Diffusion Probe: Generated Image Result Prediction Using CNN Probes
扩散探针:利用CNN探针进行生成图像结果预测
Benlei Cui, Bukun Huang, Zhizeng Ye, Xuemei Dong, Tuo Chen, Hui Xue, Dingkang Yang, Longtao Huang, Jingqun Tang, Haiwen Hong
机构
*
Alibaba Group(阿里巴巴集团)
;
Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, School of Statistics and Data Science, Zhejiang Gongshang University(浙江工商大学统计与数据科学学院共同富裕统计监测与智能治理实验室)
;
Southeast University(东南大学)
;
College of Intelligent Robotics and Advanced Manufacturing, Fudan University(复旦大学智能机器人与先进制造学院)
;
ByteDance Inc.(字节跳动有限公司)
CommentsPresented at the 2026 AAS/AIAA Astrodynamics Specialist Conference in Whistler, BC, Canada. v2 - corrected title metadata, content remains unchanged
Journal refNayak, A., Gentine, P., and Lall, U. (2026). "Attention-Based Stochastic Simulation of Climate-Informed Spatiotemporal Flood Risk for Multisite Insurance Portfolios." Geophysical Research Letters, 53 (15)