大模型对齐与安全 - arXivDaily 专题

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

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)

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

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)

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

2508.17653 2025-08-26 cs.CV 50%

FloraSyntropy-Net: Scalable Deep Learning with Novel FloraSyntropy Archive for Large-Scale Plant Disease Diagnosis

Saif Ur Rehman Khan, Muhammad Nabeel Asim, Sebastian Vollmer, Andreas Dengel

机构 * German Research Center for Artificial Intelligence（德国人工智能研究中心）； Intelligentx GmbH

专题命中隐私与版权：safety(abstract)

2508.07672 2025-08-12 cs.HC 50%

Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences

Shuning Zhang, Ying Ma, Jingruo Chen, Simin Li, Xin Yi, Hewu Li

专题命中隐私与版权：alignment(abstract)

2508.07664 2025-08-12 cs.HC 50%

Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory

Shuning Zhang, Rongjun Ma, Ying Ma, Shixuan Li, Yiqun Xu, Xin Yi, Hewu Li

专题命中隐私与版权：trustworthy(abstract)

2506.11371 2025-06-16 cs.CV 50%

A Watermark for Auto-Regressive Image Generation Models

Yihan Wu, Xuehao Cui, Ruibo Chen, Georgios Milis, Heng Huang

机构 * University of Maryland, College Park（马里兰大学 College Park分校）

专题命中隐私与版权：trustworthy(abstract)

Comments Technical report

2506.01657 2025-06-12 quant-ph 50%

State Similarity in Modular Superconducting Quantum Processors with Classical Communications

Bujiao Wu, Changrong Xie, Peng Mi, Zhiyi Wu, Zechen Guo, Peisheng Huang, Wenhui Huang, Xuandong Sun, Jiawei Zhang, Libo Zhang, Jiawei Qiu, Xiayu Linpeng, Ziyu Tao, Ji Chu, Ji Jiang, Song Liu, Jingjing Niu, Yuxuan Zhou, Yuxuan Du, Wenhui Ren, Youpeng Zhong, Tongliang Liu, Dapeng Yu

专题命中隐私与版权：trustworthy(abstract)

Comments 10 pages, 3 figures, 27-page appendix, reference citation typos corrected

2506.07894 2025-06-10 cs.CR 50%

Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption

Muhammad Ali Najjar, Ren-Yi Huang, Dumindu Samaraweera, Prashant Shekhar

专题命中隐私与版权：safety(abstract)

2504.13880 2025-06-04 cs.HC 50%

An AI-powered Public Health Automated Kiosk System for Personalized Care: An Experimental Pilot Study

Sonya Falahati, Morteza Alizadeh, Fatemeh Ghazipour, Zhino Safahi, Navid Khaledian, Mohammad R. Salmanpour

专题命中隐私与版权：safety(abstract)

Comments 16 pages, 3 figures, 2 tables

2506.01072 2025-06-03 cs.CR 50%

IDCloak: A Practical Secure Multi-party Dataset Join Framework for Vertical Privacy-preserving Machine Learning

Shuyu Chen, Guopeng Lin, Haoyu Niu, Lushan Song, Chengxun Hong, Weili Han

专题命中隐私与版权：alignment(abstract)

2505.14085 2025-05-21 cs.NI 50%

CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration

Pengyan Zhu, Tingting Yang

专题命中隐私与版权：alignment(abstract)

Comments 14 pages, 7 figures including subplots

2505.07306 2025-05-13 cs.CV 50%

Enabling Privacy-Aware AI-Based Ergonomic Analysis

Sander De Coninck, Emilio Gamba, Bart Van Doninck, Abdellatif Bey-Temsamani, Sam Leroux, Pieter Simoens

专题命中隐私与版权：safety(abstract)

Comments Accepted and presented at the 35th CIRP Design conference

2505.06749 2025-05-13 eess.SY cs.SY 50%

AI-CDA4All: Democratizing Cooperative Autonomous Driving for All Drivers via Affordable Dash-cam Hardware and Open-source AI Software

Shengming Yuan, Hao Zhou

专题命中隐私与版权：safety(abstract)

Comments 8 pages, 10 figures

2505.01973 2025-05-06 cs.CV 50%

Visual Dominance and Emerging Multimodal Approaches in Distracted Driving Detection: A Review of Machine Learning Techniques

Anthony Dontoh, Stephanie Ivey, Logan Sirbaugh, Andrews Danyo, Armstrong Aboah

专题命中隐私与版权：safety(abstract)

2504.18349 2025-04-28 cs.CV cs.CR 50%

Revisiting Data Auditing in Large Vision-Language Models

Hongyu Zhu, Sichu Liang, Wenwen Wang, Boheng Li, Tongxin Yuan, Fangqi Li, ShiLin Wang, Zhuosheng Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； Southeast University（东南大学）； Carnegie Mellon University（卡内基梅隆大学）； Nanyang Technological University（南洋理工大学）

专题命中隐私与版权：trustworthy(abstract)

2504.13267 2025-04-21 cs.CR cs.SY eess.SY 50%

Leveraging Functional Encryption and Deep Learning for Privacy-Preserving Traffic Forecasting

Isaac Adom, Mohammmad Iqbal Hossain, Hassan Mahmoud, Ahmad Alsharif, Mahmoud Nabil Mahmoud, Yang Xiao

专题命中隐私与版权：safety(abstract)

Comments 17 pages, 14 Figures, Journal Publication

2504.11783 2025-04-17 cs.CR 50%

The Digital Cybersecurity Expert: How Far Have We Come?

Dawei Wang, Geng Zhou, Xianglong Li, Yu Bai, Li Chen, Ting Qin, Jian Sun, Dan Li

专题命中隐私与版权：alignment(abstract)

Comments To appear in the IEEE Symposium on Security and Privacy (IEEE S&P) 2025, San Francisco, CA, USA

2503.16171 2025-03-21 cs.CV 50%

Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation

Soham Roy, Abhishek Mishra, Shirish Karande, Murari Mandal

专题命中隐私与版权：alignment(abstract)

2502.16383 2025-02-27 cs.HC 50%

Understanding Generative AI Risks for Youth: A Taxonomy Based on Empirical Data

Yaman Yu, Yiren Liu, Jacky Zhang, Yun Huang, Yang Wang

专题命中隐私与版权：safety(abstract)

2406.09037 2025-02-27 cs.HC 50%

Evaluating Privacy, Security, and Trust Perceptions in Conversational AI: A Systematic Review

Anna Leschanowsky, Silas Rech, Birgit Popp, Tom Bäckström

专题命中隐私与版权：trustworthy(abstract)

Comments 39 pages, 4 figures

2502.16094 2025-02-25 cs.CR 50%

Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging

Lin Lu, Zhigang Zuo, Ziji Sheng, Pan Zhou

专题命中隐私与版权：alignment(abstract)

Comments 17 pages, 3 figures

2412.07954 2025-01-31 cs.CR 50%

MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference

Parsa Ghazvinian, Robert Podschwadt, Prajwal Panzade, Mohammad H. Rafiei, Daniel Takabi

专题命中隐私与版权：alignment(abstract)

Comments 10 pages, 5 Figures, IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications 2024

2412.14768 2024-12-20 cs.CV 50%

FLAMe: Federated Learning with Attention Mechanism using Spatio-Temporal Keypoint Transformers for Pedestrian Fall Detection in Smart Cities

Byeonghun Kim, Byeongjoon Noh

专题命中隐私与版权：safety(abstract)

Comments 8 pages, 7 figures, AAAI 2025 FLUID Workshop

2407.04346 2024-12-09 cs.CV 50%

MobileFlow: A Multimodal LLM For Mobile GUI Agent

Songqin Nong, Jiali Zhu, Rui Wu, Jiongchao Jin, Shuo Shan, Xiutian Huang, Wenhao Xu

专题命中隐私与版权：alignment(abstract)

2404.16824 2024-11-15 cs.CV 50%

V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection

Xuanyu Zhang, Youmin Xu, Runyi Li, Jiwen Yu, Weiqi Li, Zhipei Xu, Jian Zhang

专题命中隐私与版权：alignment(abstract)

Comments Accepted by ACM MM 2024

2410.01844 2024-10-15 cs.SI 50%

Urban Anomalies: A Simulated Human Mobility Dataset with Injected Anomalies

Hossein Amiri, Ruochen Kong, Andreas Zufle

专题命中隐私与版权：safety(abstract)

Comments This is an accepted paper on https://onspatial.github.io/GeoAnomalies24/

2409.09582 2024-09-25 cs.CV 50%

NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training

Yiyi Tao, Zhuoyue Wang, Hang Zhang, Lun Wang

专题命中隐私与版权：alignment(abstract)

1. 隐私与版权 691 篇

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

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

Image-guided topic modeling for interpretable privacy classification

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

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

FloraSyntropy-Net: Scalable Deep Learning with Novel FloraSyntropy Archive for Large-Scale Plant Disease Diagnosis

Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences

Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory

A Watermark for Auto-Regressive Image Generation Models

State Similarity in Modular Superconducting Quantum Processors with Classical Communications

Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption

An AI-powered Public Health Automated Kiosk System for Personalized Care: An Experimental Pilot Study

IDCloak: A Practical Secure Multi-party Dataset Join Framework for Vertical Privacy-preserving Machine Learning

CE-LSLM: Efficient Large-Small Language Model Inference and Communication via Cloud-Edge Collaboration

Enabling Privacy-Aware AI-Based Ergonomic Analysis

AI-CDA4All: Democratizing Cooperative Autonomous Driving for All Drivers via Affordable Dash-cam Hardware and Open-source AI Software

Visual Dominance and Emerging Multimodal Approaches in Distracted Driving Detection: A Review of Machine Learning Techniques

Revisiting Data Auditing in Large Vision-Language Models

Leveraging Functional Encryption and Deep Learning for Privacy-Preserving Traffic Forecasting

The Digital Cybersecurity Expert: How Far Have We Come?

Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation

Understanding Generative AI Risks for Youth: A Taxonomy Based on Empirical Data

Evaluating Privacy, Security, and Trust Perceptions in Conversational AI: A Systematic Review

Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging

MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference

FLAMe: Federated Learning with Attention Mechanism using Spatio-Temporal Keypoint Transformers for Pedestrian Fall Detection in Smart Cities

MobileFlow: A Multimodal LLM For Mobile GUI Agent

V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection

Urban Anomalies: A Simulated Human Mobility Dataset with Injected Anomalies

NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training