arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

共收录 686 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 隐私与版权 686 篇

2512.06033 2026-03-25 cs.CR econ.GN q-fin.EC 50%

Sell Data to AI Algorithms Without Revealing It: Secure Data Valuation and Sharing via Homomorphic Encryption

将数据出售给AI算法而不揭露它:通过同态加密实现安全的数据估值与分享

Michael Yang, Ruijiang Gao, Zhiqiang Zheng

专题命中 隐私与版权 :trustworthy(abstract)

AI总结 本文提出Trustworthy Influence Protocol,利用同态加密和梯度影响函数,在不解密数据的情况下评估外部数据的效用,验证了其在医疗和生成AI领域的经济潜力,挑战了现有定价模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18415 2026-03-24 cs.HC 50%

AI-Wrapped: Participatory, Privacy-Preserving Measurement of Longitudinal LLM Use In-the-Wild

AI-Wrapped:参与式、隐私保护的长期LLM使用情况实地测量

Cathy Mengying Fang, Sheer Karny, Chayapatr Archiwaranguprok, Yasith Samaradivakara, Pat Pataranutaporn, Pattie Maes

专题命中 隐私与版权 :alignment(abstract)

AI总结 本文提出AI-Wrapped系统,通过隐私保护的方式收集真实LLM聊天使用数据,并分析用户使用模式及主题,揭示用户在日常场景中对LLM的使用特点及潜在问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.11877 2026-03-13 eess.AS 50%

Silent Speech Interfaces in the Era of Large Language Models: A Comprehensive Taxonomy and Systematic Review

在大语言模型时代的大声接口:全面的分类法和系统性综述

Kele Xu, Yifan Wang, Ming Feng, Qisheng Xu, Wuyang Chen, Yutao Dou, Cheng Yang, Huaimin Wang

专题命中 隐私与版权 :alignment(abstract)

AI总结 本文综述了在大语言模型时代无声语音接口的发展,探讨了从传统传感器到意图执行的分类法,分析了生物信号处理的转变,并提出了未来发展方向和伦理边界。

Comments 20 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03406 2026-03-13 cs.HC 50%

AI Chatbots or Human Therapists? Belief-Based Predictors of Mental Health Help-Seeking Intentions in the Age of Generative AI

人工智能聊天机器人还是人类治疗师?在生成式人工智能时代的基于信念的心理健康求助意图预测

Junsang Park, Sarah Brown, David L. Vogel, Nan Zhao, Sharon Lynn Chu

专题命中 隐私与版权 :trustworthy(abstract)

AI总结 本研究探讨了生成式人工智能时代人们在使用AI聊天机器人和人类治疗师之间的选择,发现人际支持和经济因素影响求助意图。

Comments v2: Corrected analysis; updated results, introduction, and discussion accordingly

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.13941 2026-02-17 cs.HC 50%

Avoiding Social Judgment, Seeking Privacy: Investigating why Mothers Shift from Facebook Groups to Large Language Models

避免社会评判,寻求隐私:探究母亲为何从Facebook群组转向大型语言模型

Shayla Sharmin, Sadia Afrin

专题命中 隐私与版权 :safety(abstract)

AI总结 研究探讨母亲为何从Facebook群组转向LLM,发现社会评判和隐私需求驱动这一转变,LLM提供即时且安全的支持替代方案。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11223 2026-02-13 cs.SE cs.HC 50%

Patient Digital Twins for Chronic Care: Technical Hurdles, Lessons Learned, and the Road Ahead

慢性病护理中的患者数字双胞胎:技术障碍、经验教训与未来之路

Micheal P. Papazoglou, Bernd J. Krämer, Mira Raheem, Amal Elgammal

专题命中 隐私与版权 :trustworthy(abstract)

AI总结 本文探讨了患者医疗数字双胞胎在慢性病护理中的技术挑战与未来发展方向,提出了基于本体驱动建模和联邦分析的实施方法,并强调了标准对齐、隐私治理和多模态推理等关键技术。

Comments Feature Article, Patient Medical Digital Twins, Under Review in IEEE SOftware

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10251 2026-02-12 cs.HC cs.CR 50%

Actions Speak Louder Than Chats: Investigating AI Chatbot Age Gating

行动胜于聊天:研究AI聊天机器人年龄限制

Olivia Figueira, Pranathi Chamarthi, Tu Le, Athina Markopoulou

专题命中 隐私与版权 :safety(abstract)

AI总结 本文研究流行聊天机器人是否能通过对话估计用户年龄并采取行动限制儿童访问,发现其未能履行自身政策。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17118 2026-02-10 cs.CR 50%

Constant-Size Cryptographic Evidence Structures for Regulated AI Workflows

固定大小的加密证据结构用于受监管的AI工作流

Leo Kao

专题命中 隐私与版权 :alignment(abstract)

AI总结 本文提出固定大小的加密证据结构,用于受监管AI工作流,以实现强绑定、固定存储和统一验证,适用于临床试验、医疗决策支持等场景。

Comments 16 pages, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.20161 2026-02-02 cs.HC 50%

Supporting Informed Self-Disclosure: Design Recommendations for Presenting AI-Estimates of Privacy Risks to Users

支持知情自我披露:为向用户呈现AI估计的隐私风险提供设计建议

Isadora Krsek, Meryl Ye, Wei Xu, Alan Ritter, Laura Dabbish, Sauvik Das

专题命中 隐私与版权 :safety(abstract)

AI总结 本文通过设计虚构和漫画板方法,提出四个设计建议,帮助用户理解AI估计的隐私风险,以促进知情的自我披露决策。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01140 2026-01-05 q-bio.OT 50%

Open Data Sharing in Clinical Research and Participants Privacy: Challenges and Opportunities in the Era of Artificial Intelligence

临床研究中的开放数据共享与参与者隐私:人工智能时代的挑战与机遇

Shahin Hallaj, Anna Heinke, Fritz Gerald P. Kalaw, Nayoon Gim, Marian Blazes, Julia Owen, Eamon Dysinger, Erik S. Benton, Benjamin A. Cordier, Nicholas G. Evans, Jennifer Li-Pook-Than, Michael P. Snyder, Camille Nebeker, Linda M. Zangwill, Sally L. Baxter, Shannon McWeeney, Cecilia S. Lee, Aaron Y. Lee, Bhavesh Patel

专题命中 隐私与版权 :safety(abstract)

AI总结 本文探讨了人工智能时代临床研究中开放数据共享与参与者隐私保护的挑战与机遇,提出伪重新识别概念并介绍了新型开放数据共享方法。

Journal ref eClinicalMedicine. 2026;91:103729

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20858 2025-12-25 cs.CV 50%

ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interaction

ALIVE: 一种具有内容感知检索的虚拟形象-讲座交互视频引擎,用于实时交互

Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang

机构 * Department of Computer Science Rensselaer Polytechnic Institute(计算机科学系罗切斯特理工学院) Department of Biomedical Engineering Rensselaer Polytechnic Institute(生物医学工程系罗切斯特理工学院)

专题命中 隐私与版权 :alignment(abstract)

AI总结 ALIVE通过本地部署和内容感知检索,实现基于虚拟形象的实时互动学习,提升讲座的教育价值。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.05031 2025-12-09 cs.IR 50%

LSRP: A Leader-Subordinate Retrieval Framework for Privacy-Preserving Cloud-Device Collaboration

LSRP: 一种用于隐私保护云-设备协作的领导者-下属检索框架

Yingyi Zhang, Pengyue Jia, Xianneng Li, Derong Xu, Maolin Wang, Yichao Wang, Zhaocheng Du, Huifeng Guo, Yong Liu, Ruiming Tang, Xiangyu Zhao

专题命中 隐私与版权 :DPO(abstract)

AI总结 LSRP通过领导者-下属检索框架提升云-设备协作的隐私保护性能,增强云模型与设备模型的协同能力。

Comments Accepted at KDD'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02861 2025-12-03 cs.NI 50%

Network Self-Configuration based on Fine-Tuned Small Language Models

基于微调小语言模型的网络自配置

Oscar G. Lira, Oscar M. Caicedo, Nelson L. S. Da Fonseca

专题命中 隐私与版权 :alignment(abstract)

AI总结 本文提出SLM_netconfig,一种基于微调小语言模型的网络自配置框架,通过参数高效适应技术实现高效、准确且隐私保护的本地化配置生成。

Comments 16 pages, 11 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.16181 2025-11-26 cs.CV 50%

CLIP-IT: CLIP-based Pairing for Histology Images Classification

CLIP-IT: 基于CLIP的病理图像分类配对

Banafsheh Karimian, Giulia Avanzato, Soufian Belharbi, Alexis Guichemerre, Luke McCaffrey, Mohammadhadi Shateri, Eric Granger

机构 * LIVIA, ILLS, Dept. of Systems Engineering, ETS Montreal, Canada(LIVIA、ILLs、系统工程系、蒙特利尔大学ETSMontreal加拿大) Dept. of Computer Engineering, University of Cagliari, Italy(计算机工程系、卡利亚里大学意大利) Goodman Cancer Research, Centre, Dept. of Oncology, McGill University, Canada(Goodman癌症研究中心、肿瘤学系、麦吉尔大学加拿大)

专题命中 隐私与版权 :alignment(abstract)

AI总结 CLIP-IT通过利用未配对的病理报告提升病理图像分类性能,无需配对数据或复杂推理。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02001 2025-11-11 cs.DC 50%

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models

Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang

专题命中 隐私与版权 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02055 2025-11-05 cs.CR 50%

Private Map-Secure Reduce: Infrastructure for Efficient AI Data Markets

Sameer Wagh, Kenneth Stibler, Shubham Gupta, Lacey Strahm, Irina Bejan, Jiahao Chen, Dave Buckley, Ruchi Bhatia, Jack Bandy, Aayush Agarwal, Andrew Trask

专题命中 隐私与版权 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22964 2025-10-28 cs.CV 50%

Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges

Liling Yang, Ning Chen, Jun Yue, Yidan Liu, Jiayi Ma, Pedram Ghamisi, Antonio Plaza, Leyuan Fang

机构 * School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院) Institute of Remote Sensing and Geographic Information System, Peking University(北京大学遥感与地理信息系统研究所) School of Automation, Central South University(中南大学自动化学院) Electronic Information School, Wuhan University(武汉大学电子信息学院) Helmholtz-Zentrum Dresden-Rossendorf(德累斯顿-罗斯托克亥姆霍尔茨中心) Lancaster Environment Centre, Lancaster University(兰卡斯特大学环境研究中心) Hyperspectral Computing Laboratory, Department of Technology of Computers and Communications, Escuela Politécnica, University of Extremadura(埃斯特雷马杜拉大学技术计算机与通讯系超光谱计算实验室)

专题命中 隐私与版权 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13136 2025-10-16 cs.CR 50%

Privacy-Aware Framework of Robust Malware Detection in Indoor Robots: Hybrid Quantum Computing and Deep Neural Networks

Tan Le, Van Le, Sachin Shetty

专题命中 隐私与版权 :trustworthy(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06480 2025-10-09 cs.HC 50%

AI Eyes on the Road: Cross-Cultural Perspectives on Traffic Surveillance

Ziming Wang, Shiwei Yang, Rebecca Currano, Morten Fjeld, David Sirkin

专题命中 隐私与版权 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24043 2025-09-30 cs.CR 50%

An Ensemble Framework for Unbiased Language Model Watermarking

Yihan Wu, Ruibo Chen, Georgios Milis, Heng Huang

专题命中 隐私与版权 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15894 2025-09-25 cs.OS 50%

MVVM: Deploy Your AI Agents-Securely, Efficiently, Everywhere

Yiwei Yang, Aibo Hu, Yusheng Zheng, Brian Zhao, Xinqi Zhang, Dawei Xiang, Kexin Chu, Wei Zhang, Andi Quinn

专题命中 隐私与版权 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19041 2025-09-24 cs.HC 50%

Position: Human-Robot Interaction in Embodied Intelligence Demands a Shift From Static Privacy Controls to Dynamic Learning

Shuning Zhang, Hong Jia, Simin Li, Ting Dang, Yongquan `Owen' Hu, Xin Yi, Hewu Li

专题命中 隐私与版权 :trustworthy(abstract)

Comments To be published in NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13072 2025-09-17 cs.CR 50%

Digital Sovereignty Control Framework for Military AI-based Cyber Security

Clara Maathuis, Kasper Cools

专题命中 隐私与版权 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.07084 2025-09-12 cs.RO 50%

DriveSOTIF: Advancing Perception SOTIF Through Multimodal Large Language Models

Shucheng Huang, Freda Shi, Chen Sun, Jiaming Zhong, Minghao Ning, Yufeng Yang, Yukun Lu, Hong Wang, Amir Khajepour

机构 * MVSLab, Department of Mechanical and Mechatronics Engineering, University of Waterloo(滑铁卢大学机械与机电工程系MVSLab) CompLING Lab, David R. Cheriton School of Computer Science, University of Waterloo(滑铁卢大学大卫·R·切里顿计算机科学学院CompLING Lab) Department of Data and Systems Engineering, University of Hong Kong(香港大学数据与系统工程系) Department of Mechanical Engineering, University of New Brunswick(新不伦瑞克大学机械工程系) School of Vehicle and Mobility, Tsinghua University(清华大学车辆与移动性学院)

专题命中 隐私与版权 :safety(abstract)

Comments This work has been accepted to IEEE Transactions on Vehicular Technology. Please refer to the copyright notice for additional information

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.00596 2025-09-11 cs.HC cs.CR 50%

Gaze3P: Gaze-Based Prediction of User-Perceived Privacy

Mayar Elfares, Pascal Reisert, Ralf Küsters, Andreas Bulling

专题命中 隐私与版权 :alignment(abstract)

Journal ref Proc. Privacy Enhancing Technologies Symposium (PETS), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08142 2025-09-11 eess.SP 50%

Privacy Preserving Semantic Communications Using Vision Language Models: A Segmentation and Generation Approach

Haoran Chang, Mingzhe Chen, Huaxia Wang, Qianqian Zhang

专题命中 隐私与版权 :alignment(abstract)

Comments 6 pages, 6 figures, Accepted at IEEE MILCOM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12490 2025-09-01 cs.CR 50%

Improving Google A2A Protocol: Protecting Sensitive Data and Mitigating Unintended Harms in Multi-Agent Systems

Yedidel Louck, Ariel Stulman, Amit Dvir

专题命中 隐私与版权 :prompt injection(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.18674 2025-08-29 cs.CV 50%

Image-guided topic modeling for interpretable privacy classification

Alina Elena Baia, Andrea Cavallaro

专题命中 隐私与版权 :alignment(abstract)

Comments Paper accepted at the eXCV Workshop at ECCV 2024. Supplementary material included. Code available at https://github.com/idiap/itm

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.19876 2025-08-28 cs.SD cs.DL 50%

The IRMA Dataset: A Structured Audio-MIDI Corpus for Iranian Classical Music

Sepideh Shafiei, Shapour Hakam

机构 * Cu Test Inc.(Cu Test公司)

专题命中 隐私与版权 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11167 2025-08-27 cs.CV 50%

VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection

Jianhong Han, Yupei Wang, Liang Chen

机构 * School of Information and Electronics, Beijing Institute of Technology(信息与电子学院,北京理工大学) Beijing Institute of Technology Chongqing Innovation Center(北京理工大学重庆创新中心) National Key Laboratory for Space-Born Intelligent Information Processing(空间智能信息处理国家重点实验室)

专题命中 隐私与版权 :alignment(abstract)

Comments Manuscript submitted to IEEE TCSVT

详情

展开后加载摘要…

URL PDF HTML 收藏