大模型对齐与安全 - arXivDaily 专题

2503.01768 2025-03-04 cs.LG cs.CV 57%

SHADE-AD: An LLM-Based Framework for Synthesizing Activity Data of Alzheimer's Patients

Heming Fu, Hongkai Chen, Shan Lin, Guoliang Xing

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

Comments 7 pages, 6 figures, ACM SenSys'25

2407.10223 2025-03-04 cs.LG cs.CR 57%

On Large Language Model Continual Unlearning

Chongyang Gao, Lixu Wang, Kaize Ding, Chenkai Weng, Xiao Wang, Qi Zhu

专题命中隐私与版权：safety(abstract)；分类 cs.LG

Comments This paper has been accepted by ICLR 2025. The first two authors contribute equally and they are ordered alphabetically

2410.11540 2025-03-03 cs.LG 57%

Data Quality Control in Federated Instruction-tuning of Large Language Models

Yaxin Du, Rui Ye, Fengting Yuchi, Wanru Zhao, Jingjing Qu, Yanfeng Wang, Siheng Chen

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

2502.14170 2025-02-21 cs.LG cs.DC 57%

Blockchain-based Framework for Scalable and Incentivized Federated Learning

Bijun Wu, Oshani Seneviratne

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

2403.13682 2025-02-18 cs.CR cs.AI 57%

Threats, Attacks, and Defenses in Machine Unlearning: A Survey

Ziyao Liu, Huanyi Ye, Chen Chen, Yongsen Zheng, Kwok-Yan Lam

专题命中隐私与版权：safety(abstract)；分类 cs.AI

Comments Accepted by IEEE Open Journal of the Computer Society

2310.12746 2025-02-18 cs.LG 57%

TabuLa: Harnessing Language Models for Tabular Data Synthesis

Zilong Zhao, Robert Birke, Lydia Chen

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

2408.02416 2025-02-13 cs.CL cs.CR 57%

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models

Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Haoyang Li

专题命中隐私与版权：safety(abstract)；分类 cs.CL

Comments Source Code: https://github.com/liangzid/PromptExtractionEval

2502.06099 2025-02-11 cs.LG 57%

Fine-Tuning Federated Learning-Based Intrusion Detection Systems for Transportation IoT

Robert Akinie, Nana Kankam Brym Gyimah, Mansi Bhavsar, John Kelly

专题命中隐私与版权：safety(abstract)；分类 cs.LG

Comments 7 pages, 4 figures. To be published in IEEE SouthEastCon 2025

2501.19338 2025-02-03 eess.IV cs.AI cs.CV 57%

Pathological MRI Segmentation by Synthetic Pathological Data Generation in Fetuses and Neonates

Misha P. T Kaandorp, Damola Agbelese, Hosna Asma-ull, Hyun-Gi Kim, Kelly Payette, Patrice Grehten, Gennari Antonio Giulio, Levente István Lánczi, Andras Jakab

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

Comments 30 pages, 4 figures, 5 tables

2501.06177 2025-01-13 cs.ET cs.CY cs.HC 57%

ScooterLab: A Programmable and Participatory Sensing Research Testbed using Micromobility Vehicles

Ubaidullah Khan, Raveen Wijewickrama, Buddhi Ashan M. K., A. H. M. Nazmus Sakib, Khoi Trinh, Christina Duthie, Nima Najafian, Ahmer Patel, R. N. Molina, Anindya Maiti, Sushil K. Prasad, Greg P. Griffin, Murtuza Jadliwala

专题命中隐私与版权：safety(abstract)；分类 cs.CY

2501.02461 2025-01-07 cs.CV cs.AI 57%

FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Models

Hui Lin, Chao Zhang, Danfeng Hong, Kexin Dong, Congcong Wen

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

2409.09739 2024-12-18 cs.CR cs.CL 57%

PersonaMark: Personalized LLM watermarking for model protection and user attribution

Yuehan Zhang, Peizhuo Lv, Yinpeng Liu, Yongqiang Ma, Wei Lu, Xiaofeng Wang, Xiaozhong Liu, Jiawei Liu

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

Comments Under review

2412.02538 2024-12-05 cs.IT cs.LG eess.SP math.IT 57%

On Privacy, Security, and Trustworthiness in Distributed Wireless Large AI Models (WLAM)

Zhaohui Yang, Wei Xu, Le Liang, Yuanhao Cui, Zhijin Qin, Merouane Debbah

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

Comments 12 pages, 4 figures

2411.07468 2024-11-14 cs.CR cs.LG 57%

Privacy-Preserving Verifiable Neural Network Inference Service

Arman Riasi, Jorge Guajardo, Thang Hoang

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

Comments Accepted at the Annual Computer Security Applications Conference (ACSAC) 2024. Source code: github.com/vt-asaplab/vPIN

2411.01136 2024-11-05 cs.CL 57%

Do LLMs Know to Respect Copyright Notice?

Jialiang Xu, Shenglan Li, Zhaozhuo Xu, Denghui Zhang

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

Comments EMNLP 2024 main

2111.12444 2024-10-28 cs.IT cs.LG cs.NI eess.SP math.IT 57%

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Khaled B. Letaief, Yuanming Shi, Jianmin Lu, Jianhua Lu

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

Comments This work is a JSAC invited survey & tutorial paper

2406.12752 2024-10-15 cs.CR cs.CV cs.LG 57%

Extracting Training Data from Unconditional Diffusion Models

Yunhao Chen, Xingjun Ma, Difan Zou, Yu-Gang Jiang

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

Comments This is an old version of arXiv:2410.02467. Please refer to the new version

2406.15992 2024-10-14 cs.CL 57%

Can LLM Graph Reasoning Generalize beyond Pattern Memorization?

Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xiaochuang Han, Tianxing He, Yulia Tsvetkov

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

Comments 17 pages, 6 figures. EMNLP 2024 Findings. Code and data is publicly available at https://github.com/MatthewYZhang/NLGift

2407.03103 2024-10-08 cs.CL 57%

Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

Suyeon Lee, Sunghwan Kim, Minju Kim, Dongjin Kang, Dongil Yang, Harim Kim, Minseok Kang, Dayi Jung, Min Hee Kim, Seungbeen Lee, Kyoung-Mee Chung, Youngjae Yu, Dongha Lee, Jinyoung Yeo

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

Comments Published at EMNLP 2024 Findings

2310.10383 2024-10-01 cs.CL cs.CR 57%

Privacy in Large Language Models: Attacks, Defenses and Future Directions

Haoran Li, Yulin Chen, Jinglong Luo, Jiecong Wang, Hao Peng, Yan Kang, Xiaojin Zhang, Qi Hu, Chunkit Chan, Zenglin Xu, Bryan Hooi, Yangqiu Song

专题命中隐私与版权：safety(abstract)；分类 cs.CL

Comments We upload the survey to cover more recent papers and inlcude privacy resaearch on multi-modality

2409.04574 2024-09-10 cs.CL 57%

Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning

Xinyue Liu, Harshita Diddee, Daphne Ippolito

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

2402.05731 2024-09-04 cs.CY 57%

Face Recognition: to Deploy or not to Deploy? A Framework for Assessing the Proportional Use of Face Recognition Systems in Real-World Scenarios

Pablo Negri, Isabelle Hupont, Emilia Gomez

专题命中隐私与版权：safety(abstract)；分类 cs.CY

Comments Published a shorter version in IEEE International Conference on Automatic Face and Gesture Recognition 2024

2408.11649 2024-08-22 cs.CV cs.AI 57%

Video-to-Text Pedestrian Monitoring (VTPM): Leveraging Computer Vision and Large Language Models for Privacy-Preserve Pedestrian Activity Monitoring at Intersections

Ahmed S. Abdelrahman, Mohamed Abdel-Aty, Dongdong Wang

专题命中隐私与版权：safety(abstract)；分类 cs.AI

2310.15848 2024-08-20 cs.LG cs.CV 57%

On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms

Surbhi Mittal, Kartik Thakral, Richa Singh, Mayank Vatsa, Tamar Glaser, Cristian Canton Ferrer, Tal Hassner

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

Comments This preprint has not undergone any post-submission improvements or corrections. The Version of Record of this article is published in Nature Machine Intelligence and is available online at https://doi.org/10.1038/s42256-024-00874-y

2408.00050 2024-08-02 stat.ML cs.DC cs.LG 57%

Algorithms for Collaborative Machine Learning under Statistical Heterogeneity

Seok-Ju Hahn

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

Comments Doctoral Dissertation. For the conference version of Chapter II, see arXiv:2109.07628v3, and for the conference version of Chapter III, see arXiv:2405.20821v1

2407.07054 2024-07-10 cs.CR cs.ET cs.LG 57%

A Differentially Private Blockchain-Based Approach for Vertical Federated Learning

Linh Tran, Sanjay Chari, Md. Saikat Islam Khan, Aaron Zachariah, Stacy Patterson, Oshani Seneviratne

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

2407.01561 2024-07-03 eess.IV cs.AI cs.CV 57%

Synthetic Data in Radiological Imaging: Current State and Future Outlook

Elena Sizikova, Andreu Badal, Jana G. Delfino, Miguel Lago, Brandon Nelson, Niloufar Saharkhiz, Berkman Sahiner, Ghada Zamzmi, Aldo Badano

专题命中隐私与版权：safety(abstract)；分类 cs.AI

Comments Provisionally accepted to the British Journal of Radiology (BJR) Artificial Intelligence

2406.17899 2024-06-27 cs.LG cs.CV cs.DC 57%

Entity Augmentation for Efficient Classification of Vertically Partitioned Data with Limited Overlap

Avi Amalanshu, Viswesh Nagaswamy, G. V. S. S. Prudhvi, Yash Sirvi, Debashish Chakravarty

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

Comments GLOW @ IJCAI 2024 (12 pages + 2 page bibliography. 15 figures.)

2311.09538 2024-06-25 cs.CL cs.HC 57%

Reducing Privacy Risks in Online Self-Disclosures with Language Models

Yao Dou, Isadora Krsek, Tarek Naous, Anubha Kabra, Sauvik Das, Alan Ritter, Wei Xu

专题命中隐私与版权：safety(abstract)；分类 cs.CL

Comments Accepted at ACL 2024

2406.05651 2024-06-11 cs.RO cs.CL cs.CV 57%

A Superalignment Framework in Autonomous Driving with Large Language Models

Xiangrui Kong, Thomas Braunl, Marco Fahmi, Yue Wang

专题命中隐私与版权：safety(abstract)；分类 cs.CL

Comments 6 pages, 5 figures, ieeeiv24

1. 隐私与版权 686 篇

SHADE-AD: An LLM-Based Framework for Synthesizing Activity Data of Alzheimer's Patients

On Large Language Model Continual Unlearning

Data Quality Control in Federated Instruction-tuning of Large Language Models

Blockchain-based Framework for Scalable and Incentivized Federated Learning

Threats, Attacks, and Defenses in Machine Unlearning: A Survey

TabuLa: Harnessing Language Models for Tabular Data Synthesis

Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models

Fine-Tuning Federated Learning-Based Intrusion Detection Systems for Transportation IoT

Pathological MRI Segmentation by Synthetic Pathological Data Generation in Fetuses and Neonates

ScooterLab: A Programmable and Participatory Sensing Research Testbed using Micromobility Vehicles

FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Models

PersonaMark: Personalized LLM watermarking for model protection and user attribution

On Privacy, Security, and Trustworthiness in Distributed Wireless Large AI Models (WLAM)

Privacy-Preserving Verifiable Neural Network Inference Service

Do LLMs Know to Respect Copyright Notice?

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Extracting Training Data from Unconditional Diffusion Models

Can LLM Graph Reasoning Generalize beyond Pattern Memorization?

Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

Privacy in Large Language Models: Attacks, Defenses and Future Directions

Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning

Face Recognition: to Deploy or not to Deploy? A Framework for Assessing the Proportional Use of Face Recognition Systems in Real-World Scenarios

Video-to-Text Pedestrian Monitoring (VTPM): Leveraging Computer Vision and Large Language Models for Privacy-Preserve Pedestrian Activity Monitoring at Intersections

On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms

Algorithms for Collaborative Machine Learning under Statistical Heterogeneity

A Differentially Private Blockchain-Based Approach for Vertical Federated Learning

Synthetic Data in Radiological Imaging: Current State and Future Outlook

Entity Augmentation for Efficient Classification of Vertically Partitioned Data with Limited Overlap

Reducing Privacy Risks in Online Self-Disclosures with Language Models

A Superalignment Framework in Autonomous Driving with Large Language Models