大模型对齐与安全

Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks

Jan Aalmoes, Vasisht Duddu, Antoine Boutet

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

Comments The paper's results and conclusions underwent significant changes. The updated paper can be found at arXiv:2211.10209

Privacy and Transparency in Graph Machine Learning: A Unified Perspective

Megha Khosla

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

Comments In Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI) at International Conference on Information and Knowledge Management (CIKM'22)

Targeted Honeyword Generation with Language Models

Fangyi Yu, Miguel Vargas Martin

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

Comments 8 pages, 7 tables, 2 figures

Federated Learning in Vehicular Networks

Ahmet M. Elbir, Burak Soner, Sinem Coleri, Deniz Gunduz, Mehdi Bennis

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 2022 IEEE International Mediterranean Conference on Communications and Networking (MeditCom)

Distributed learning optimisation of Cox models can leak patient data: Risks and solutions

Carsten Brink, Christian Rønn Hansen, Matthew Field, Gareth Price, David Thwaites, Nis Sarup, Uffe Bernchou, Lois Holloway

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 51 pages, 8 figures

FlowSense: Monitoring Airflow in Building Ventilation Systems Using Audio Sensing

Bhawana Chhaglani, Camellia Zakaria, Adam Lechowicz, Prashant Shenoy, Jeremy Gummeson

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 26 pages, 12 figures, Will appear in March issue of the IMWUT 2022 journal

Enhancing the Security & Privacy of Wearable Brain-Computer Interfaces

Zahra Tarkhani, Lorena Qendro, Malachy O'Connor Brown, Oscar Hill, Cecilia Mascolo, Anil Madhavapeddy

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Towards the Internet of Behaviors in airports with a fog-to-cloud approach

Antonio Salis

专题命中 隐私与版权 ：safety(abstract)；分类 cs.CY

Comments 16 pages, 10 figures;

Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification

Dominique Mercier, Adriano Lucieri, Mohsin Munir, Andreas Dengel, Sheraz Ahmed

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Comments 9 pages, 4 figures. 6 tables

CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training

Hari Prasanna Das, Ryan Tran, Japjot Singh, Yu-Wen Lin, Costas J. Spanos

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

Comments Workshop on Machine Learning for Data: Automated Creation,Privacy, Bias, In 38th International Conference on Machine Learning (ICML) 2021

Model Extraction and Adversarial Attacks on Neural Networks using Switching Power Information

Tommy Li, Cory Merkel

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Robust error bounds for quantised and pruned neural networks

Jiaqi Li, Ross Drummond, Stephen R. Duncan

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

SecureBoost: A Lossless Federated Learning Framework

Kewei Cheng, Tao Fan, Yilun Jin, Yang Liu, Tianjian Chen, Dimitrios Papadopoulos, Qiang Yang

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

On the Privacy Risks of Model Explanations

Reza Shokri, Martin Strobel, Yair Zick

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

Comments 19 pages, 13 figures

Towards Compliant Data Management Systems for Healthcare ML

Goutham Ramakrishnan, Aditya Nori, Hannah Murfet, Pashmina Cameron

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

Asymmetrical Vertical Federated Learning

Yang Liu, Xiong Zhang, Libin Wang

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

FedVision: An Online Visual Object Detection Platform Powered by Federated Learning

Yang Liu, Anbu Huang, Yun Luo, He Huang, Youzhi Liu, Yuanyuan Chen, Lican Feng, Tianjian Chen, Han Yu, Qiang Yang

专题命中 隐私与版权 ：safety(abstract)；分类 cs.LG

Privacy Preserving Location Data Publishing: A Machine Learning Approach

Sina Shaham, Ming Ding, Bo Liu, Shuping Dang, Zihuai Lin, Jun Li

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

Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)

Guangxu Zhu, Yong Wang, Kaibin Huang

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

Comments This is an extended version of a submission to IEEE journal

Privacy Aware Offloading of Deep Neural Networks

Sam Leroux, Tim Verbelen, Pieter Simoens, Bart Dhoedt

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

Comments ICML 2018 Privacy in Machine Learning and Artificial Intelligence workshop

Counterfactual Influence as a Distributional Quantity

Matthieu Meeus, Igor Shilov, Georgios Kaissis, Yves-Alexandre de Montjoye

机构 * Imperial College London（帝国理工学院伦敦分校） ； Google DeepMind（谷歌DeepMind） 纠错

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

Comments Workshop on The Impact of Memorization on Trustworthy Foundation Models (MemFM) @ ICML 2025

Tensions Between the Proxies of Human Values in AI

Teresa Datta, Daniel Nissani, Max Cembalest, Akash Khanna, Haley Massa, John P. Dickerson

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

Comments Contributed Talk, NeurIPS 2022 Workshop on Algorithmic Fairness through the Lens of Causality and Privacy; To be published in 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

Mask-Free Privacy Extraction and Rewriting: A Domain-Aware Approach via Prototype Learning

无掩码隐私提取与重写：通过原型学习的领域感知方法

Xiaodong Li, Yuhua Wang, Qingchen Yu, Zixuan Qin, Yifan Sun, Qinnan Zhang, Hainan Zhang, Zhiming Zheng

专题命中 隐私与版权 ：alignment(abstract)

AI总结 本文提出DAMPER方法，通过对比学习生成领域隐私原型，实现精确的跨度定位和领域合规的重写策略，提升隐私与效用的平衡。

Comments EMNLP 2026 camera-ready. First two authors contributed equally

Beyond Natural-Image Foundation Models: Benchmarking Satellite Pretraining for Ophthalmic Image Analysis

超越自然图像基础模型：针对眼科图像分析的卫星图像预训练基准测试

Lovre Antonio Budimir, Mingya Alexa Gong, Alyssa Foong Quinney, Ivana Matovinović, Yukun Zhou, Pearse A. Keane, Sven Lončarić, Marinko V. Šarunić

机构 * Faculty of Electrical Engineering and Computing, University of Zagreb（萨格勒布大学电气工程与计算机学院） ； University College London（伦敦大学学院） ； Institute of Ophthalmology, University College London（伦敦大学学院眼科研究所） ； Department of Computer Science, University College London（伦敦大学学院计算机科学系） ； NIHR Moorfields Biomedical Research Centre（NIHR穆尔菲尔德生物医学研究中心） ； Hawkes Institute, University College London（伦敦大学学院霍克斯研究所） ； Moorfields Eye Hospital NHS Foundation Trust（穆尔菲尔德眼科医院NHS基金会信托） 纠错

专题命中 隐私与版权 ：alignment(abstract)

AI总结 本文针对眼科图像分析，对比卫星图像与自然图像预训练的视觉基础模型，发现卫星图像预训练在眼科任务上表现优于自然图像，部分任务可媲美医学专家模型。

Comments Accepted at the ECCV 2026 Workshop on Medical Foundation Models and Benchmarks (MEDFMB)

Designing Mobile and Wearable Sensor-Fused Conversational Agents for Health and Wellbeing

面向健康与福祉的移动及可穿戴传感器融合对话智能体设计

Hansoo Lee, Pablo Fonseca, Md Haseen Akhtar

专题命中 隐私与版权 ：safety(abstract)

AI总结 本教程面向健康领域，旨在教授参与者使用WSDWAS工具，将可穿戴传感器数据与LLM驱动的对话智能体结合，实现从被动监测到可操作福祉对话的转变。

Comments 6 pages, 3 figures. Accepted as a Tutorial at the 28th International Conference on Mobile Human-Computer Interaction (MobileHCI '26)

Journal ref In 28th International Conference on Mobile Human-Computer Interaction (MobileHCI '26), August 31-September 03, 2026, Swansea, United Kingdom

Examining the Effect of Explanations of AI Privacy Redaction in AI-mediated Interactions

考察AI隐私擦除解释在AI中介互动中的影响

Roshni Kaushik, Maarten Sap, Koichi Onoue

专题命中 隐私与版权 ：trustworthy(abstract)

AI总结 研究探讨AI中介互动中解释擦除操作对用户信任的影响，发现解释能提升隐私保护效果，且情境因素和个体差异影响解释效果。

Comments Accepted at AIES 2026

"Allow" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents

“允许”达成目标：移动GUI智能体中任务完成驱动的弹窗决策的意外代价

Dongsheng Chen, Yuxuan Li, Guanhua Chen, Jiaxin Zhang, Xiangyu Zhao, Lei Ma, Xin Yao, Xuetao Wei

专题命中 隐私与版权 ：safety(abstract)

AI总结 研究移动GUI智能体的权限素养，发现其存在应用信任偏差、任务优先级覆盖等问题，提示干预效果不一，建议将任务执行与权限授权分离。

YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos

YouTube-Occ：从YouTube视频学习室内3D语义占据预测

Haoming Chen, Lichen Yuan, TianFang Sun, Jingyu Gong, Xin Tan, Zhizhong Zhang, Yanyun Qu, Yuan Xie

机构 * East China Normal University（华东师范大学） 纠错

专题命中 隐私与版权 ：alignment(abstract)

AI总结 针对室内3D语义占据预测数据稀缺的问题，提出YouTube-Occ框架，通过自动化数据流水线与双对齐预训练策略，在NYUv2等基准上实现性能提升，代码数据将公开。

Comments Accepted by ECCV 2026

A literature review of recent advances in software design and architecture

软件设计与架构的最新进展文献综述

Malach Obisa Amonga

专题命中 隐私与版权 ：trustworthy(abstract)

AI总结 本文综述2024-2025年软件设计与架构研究，采用主题综合法分析五大领域，指出现代架构需覆盖全生命周期，AI辅助等技术可提升软件特性，同时存在实证验证不足等缺口。

NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling

NWaaS：一种具有自适应资源调度的非侵入性和隐私保护水印即服务系统

Haonan An, Qianyao Ren, Guang Hua, Tao Li, Yu Guo, Yanan Ma, Hangcheng Cao, Yuguang Fang

专题命中 隐私与版权 ：trustworthy(abstract)

AI总结 研究针对机器学习即服务中保护知识产权的挑战，提出NWaaS框架。核心方法包括$\mathtt{ShadowMark}$算法、协作分区机制和比例差异联合调度算法。贡献是能在多样模态中提供强大所有权验证，保障隐私并提升系统性能。