大模型对齐与安全

Multi-Continental Healthcare Modelling Using Blockchain-Enabled Federated Learning

Rui Sun, Zhipeng Wang, Hengrui Zhang, Ming Jiang, Yizhe Wen, Jiahao Sun, Erwu Liu, Kezhi Li

机构 * School of Computing, Newcastle University（新castle大学计算机学院） ； Department of Computing, Imperial College London（伦敦帝国理工学院计算机系） ； Institute of Health Informatics, University College London（伦敦大学学院健康信息学研究所） ； Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究所，同济大学） ； College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院） ； University College London Hospital（伦敦大学学院医院） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted by IEEE Global Blockchain Conference, 2025

SIMU: Selective Influence Machine Unlearning

Anu Agarwal, Mihir Pamnani, Dilek Hakkani-Tur

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted to NeurIPS 2025 Workshop: Constrained Optimization for Machine Learning (COML)

A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis

Hui Wei, Dong Yoon Lee, Shubham Rohal, Zhizhang Hu, Ryan Rossi, Shiwei Fang, Shijia Pan

机构 * Adobe Research（Adobe研究院） ； Augusta University（奥古斯塔大学） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted by CCF Transactions on Pervasive Computing and Interaction (CCF TPCI)

Accountability Capture: How Record-Keeping to Support AI Transparency and Accountability (Re)shapes Algorithmic Oversight

Shreya Chappidi, Jennifer Cobbe, Chris Norval, Anjali Mazumder, Jatinder Singh

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI、cs.CY

Comments To appear at 8th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025)

Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models

Wenjie Fu, Huandong Wang, Junyao Gao, Guoan Wan, Tao Jiang

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.LG

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents

Saswat Das, Jameson Sandler, Ferdinando Fioretto

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.AI

Machine Learning-Assisted Sustainable Remanufacturing, Reusing and Recycling for Lithium-ion Batteries

Shengyu Tao

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments This is a PhD thesis from Dr. Shengyu Tao at Tinsghua University and University of California at Berkeley

Data Valuation and Selection in a Federated Model Marketplace

Wenqian Li, Youjia Yang, Ruoxi Jia, Yan Pang

机构 * IORA National University of Singapore（国际研究机构国立新加坡大学） ； NUS Research Institution（国立新加坡大学研究机构） ； Department of ECE（电子工程系） ； Virginia Tech（弗吉尼亚理工大学） ； Business School（商学院） 纠错

专题命中 隐私与版权 ：trustworthy(abstract)；分类 cs.AI、cs.LG

HeteroTune: Efficient Federated Learning for Large Heterogeneous Models

Ruofan Jia, Weiying Xie, Jie Lei, Jitao Ma, Haonan Qin, Leyuan Fang

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments 16 pages, 4 figures

Federated Domain Generalization: A Survey

Ying Li, Xingwei Wang, Rongfei Zeng, Praveen Kumar Donta, Ilir Murturi, Min Huang, Schahram Dustdar

机构 * College of Computer Science and Engineering, Northeastern University（计算机科学与工程学院，东北大学） ； Distributed Systems Group, TU Wien（分布式系统组，TU Wien） ； College of Software, Northeastern University（软件学院，东北大学） ； College of Information Science and Engineering, Northeastern University（信息科学与工程学院，东北大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI、cs.LG

Real Time Child Abduction And Detection System

Tadisetty Sai Yashwanth, Yangalasetty Sruthi Royal, Vankayala Rajeshwari Shreya, Mayank Kashyap, Divyaprabha K N

机构 * Dept. of CSE PES University Bangalore, India（计算机科学与工程系，PES大学，印度班加罗尔） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.CY

FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models

Chuan Li, Qianyi Zhao, Fengran Mo, Cen Chen

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.AI

FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective

Zhekai Zhou, Shudong Liu, Zhaokun Zhou, Yang Liu, Qiang Yang, Yuesheng Zhu, Guibo Luo

机构 * Peking University（北京大学） ； the Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI、cs.LG

OneShield -- the Next Generation of LLM Guardrails

Chad DeLuca, Anna Lisa Gentile, Shubhi Asthana, Bing Zhang, Pawan Chowdhary, Kellen Cheng, Basel Shbita, Pengyuan Li, Guang-Jie Ren, Sandeep Gopisetty

机构 * IBM Research（IBM研究院） ； Princeton University（普林斯顿大学） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.AI

Generating Clinically Realistic EHR Data via a Hierarchy- and Semantics-Guided Transformer

Guanglin Zhou, Sebastiano Barbieri

机构 * University of Queensland（昆士兰大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments The camera ready version for ECAI-2025

"Is it always watching? Is it always listening?" Exploring Contextual Privacy and Security Concerns Toward Domestic Social Robots

Henry Bell, Jabari Kwesi, Hiba Laabadli, Pardis Emami-Naeini

机构 * Duke University（杜克大学） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.CY

Protecting Copyrighted Material with Unique Identifiers in Large Language Model Training

Shuai Zhao, Linchao Zhu, Ruijie Quan, Yi Yang

机构 * ReLER Lab, AAII, University of Technology Sydney（ReLER实验室，AAII，悉尼大学） ； ReLER Lab, CCAI, Zhejiang University（ReLER实验室，CCAI，浙江大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments A technical report, work mainly done in the early of 2024

Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach

Xiaobing Chen, Boyang Zhang, Xiangwei Zhou, Mingxuan Sun, Shuai Zhang, Songyang Zhang, Geoffrey Ye Li

机构 * Division of Electrical and Computer Engineering, Louisiana State University（电气与计算机工程系，路易斯安那州立大学） ； Division of Computer Science and Engineering, Louisiana State University（计算机科学与工程系，路易斯安那州立大学） ； Department of Data Science, New Jersey Institute of Technology（数据科学系，新泽西理工学院） ； Department of Electrical and Computer Engineering, University of Louisiana at Lafayette（电气与计算机工程系，路易斯安那大学拉斐特分校） ； Department of Electrical and Electronic Engineering, Imperial College London（电气与电子工程系，伦敦帝国理工学院） 纠错

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments 7 pages

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification

Xavier F. Cadet, Anastasia Borovykh, Mohammad Malekzadeh, Sara Ahmadi-Abhari, Hamed Haddadi

机构 * Imperial College London（伦敦帝国理工学院） ； Nokia Bell Labs（诺基亚贝尔实验室） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Accepted at EuroS&P 2025

Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks

Konstantinos Vrettos, Michail E. Klontzas

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, 3 Figures

Secure Energy Transactions Using Blockchain Leveraging AI for Fraud Detection and Energy Market Stability

Md Asif Ul Hoq Khan, MD Zahedul Islam, Istiaq Ahmed, Md Masud Karim Rabbi, Farhana Rahman Anonna, MD Abdul Fahim Zeeshan, Mehedi Hasan Ridoy, Bivash Ranjan Chowdhury, Md Nazmul Shakir Rabbi, GM Alamin Sadnan

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition

Zhiyang Qi, Keiko Takamizo, Mariko Ukiyo, Michimasa Inaba

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL、cs.AI

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation

Le Vu Anh, Nguyen Viet Anh, Mehmet Dik, Luong Van Nghia

机构 * 1 Institute of Information Technology, Vietnam Academy of Science ； 2 Institute of Information Technology, Vietnam Academy of Science ； 3 Department of Mathematics, Computer Science \& Physics, Rockford University, Illinois, United States Email ； 4 Department of Information Technology, Dong A University, Da Nang, Vietnam Email 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 7 figures, 5 tables

Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs

Flint Xiaofeng Fan, Cheston Tan, Roger Wattenhofer, Yew-Soon Ong

机构 * 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） 纠错

专题命中 隐私与版权 ：RLHF(abstract)；分类 cs.AI、cs.LG

Comments IJCNN 2025 Position Paper Track

EgoNormia: Benchmarking Physical Social Norm Understanding

MohammadHossein Rezaei, Yicheng Fu, Phil Cuvin, Caleb Ziems, Yanzhe Zhang, Hao Zhu, Diyi Yang

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.AI

Comments V4, fixes to title and formatting

Nine Ways to Break Copyright Law and Why Our LLM Won't: A Fair Use Aligned Generation Framework

Aakash Sen Sharma, Debdeep Sanyal, Priyansh Srivastava, Sundar Atreya H., Shirish Karande, Mohan Kankanhalli, Murari Mandal

专题命中 隐私与版权 ：DPO(abstract)；分类 cs.CL、cs.AI

Comments 30 Pages

On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists

Dongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi

专题命中 隐私与版权 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments Camera-ready version

Journal ref ICML 2025

A Lightweight Method to Disrupt Memorized Sequences in LLM

Parjanya Prajakta Prashant, Kaustubh Ponkshe, Babak Salimi

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CL、cs.LG

Comments 26 pages, 3 figures

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning

Shijie Liu, Andrew C. Cullen, Paul Montague, Sarah Erfani, Benjamin I. P. Rubinstein

机构 * School of Computing and Information Systems, University of Melbourne（墨尔本大学计算与信息系统学院） ； Defence Science and Technology Group（国防科学与技术集团） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Federated Learning for Cyber Physical Systems: A Comprehensive Survey

Minh K. Quan, Pubudu N. Pathirana, Mayuri Wijayasundara, Sujeeva Setunge, Dinh C. Nguyen, Christopher G. Brinton, David J. Love, H. Vincent Poor

机构 * School of Engineering, Deakin University（德克萨斯大学工程学院） ； Department of Electrical and Computer Engineering, University of Alabama in Huntsville（阿拉巴马大学亨茨维尔分校电子与计算机工程系） ； The School of Engineering, Royal Melbourne Institute of Technology University（皇家墨尔本理工学院工程学院） ； Elmore Family School of Electrical and Computer Engineering, Purdue University（普渡大学埃尔莫尔家族电子与计算机工程学院） ； Department of Electrical and Computer Engineering, Princeton University（普林斯顿大学电子与计算机工程系） 纠错

专题命中 隐私与版权 ：safety(abstract)；分类 cs.AI、cs.LG

Comments This work has been accepted by IEEE Communications Surveys & Tutorials

Journal ref IEEE Communications Surveys & Tutorials 2025