Large language models (LLMs) face diverse privacy threats, yet existing studies typically evaluate individual attacks in isolation, offering limited guidance on which system factors drive privacy vulnerabilities. This paper presents a unified threat model and a systematic ablation study of four representative attacks: Membership Inference (MIA), Attribute Inference (AIA), Data Extraction (DEA), and Backdoor Attacks (BA). Our findings reveal attack-specific sensitivities: membership inference depends strongly on dataset characteristics and attack strategy, attribute inference is influenced by model and training characteristics, data extraction increases with model scale and training-data repetition, and backdoor attacks achieve consistently high success rates. Based on these findings, we derive practical recommendations for privacy-aware LLM deployment, including prioritizing membership leakage assessments in retrieval-augmented systems, minimizing repeated personal information in training data, monitoring attribute inference risks, and safeguarding fine-tuning pipelines against backdoors.
PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院)
User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data
University of Houston(休斯顿大学);Brown University(布朗大学);University of Miami(迈阿密大学);Nagoya University(名古屋大学);University of Michigan(密歇根大学);Northern Arizona University(北亚利桑那大学)
LLM-PBE: Assessing Data Privacy in Large Language Models
University of California, Berkeley(加州大学伯克利分校);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);National University of Singapore(新加坡国立大学);Center for AI Safety(AI安全中心);University of Chicago(芝加哥大学)
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
University of Washington(华盛顿大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所);Carnegie Mellon University(卡内基梅隆大学);National University of Singapore(新加坡国立大学)
Department of Electrical and Computer Engineering, University of Pittsburgh(匹兹堡大学电气与计算机工程系);Department of Computer Science, University of Central Florida(中央佛罗里达大学计算机科学系);Department of Computer and Information Science, University of Pennsylvania(宾夕法尼亚大学计算机与信息科学系);Department of Computer Science, University of Maryland(马里兰大学计算机科学系);Department of Computer Science, Florida State University(佛罗里达州立大学计算机科学系)
A Survey: Towards Privacy and Security in Mobile Large Language Models
Department of Information Technology, Kennesaw State University(肯纳邦大学信息科技系);Department of Computer Science, Georgia State University(佐治亚州立大学计算机科学系);Nexa AI;School of Computing and Artificial Intelligence, Southwest Jiaotong University(西南交通大学计算机与人工智能学院)
Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directions
Centre for Smart Health, School of Nursing(智能健康中心、护理学院);The Hong Kong Polytechnic University(香港理工大学);Department of Electrical and Electronic Engineering(电子与电气工程系);Faculty of Health Sciences(健康科学学院);University of Maribor(马里博大学)
Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs
College of Computing and Information Science(计算与信息科学学院);Siebel School of Computing and Data Science(计算与数据科学学院);Cornell University(康奈尔大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);New York, USA(美国纽约);Champaign, Illinois, USA(美国伊利诺伊州香槟)
Can Large Language Models Really Recognize Your Name?
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Google Research(谷歌研究);Carnegie Mellon University(卡内基梅隆大学);Google Research, University of Massachusetts Amherst(谷歌研究,马萨诸塞大学阿默斯特分校);University of Maryland, College Park(马里兰大学学院市分校)
Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability
School of Cyber Science and Engineering, Shanghai Jiao Tong University(上海交通大学网络安全科学与工程学院);Institute of Cyber Security for Society (iCSS), University of Kent(肯特大学社会网络安全研究所)
Entailment-Driven Privacy Policy Classification with LLMs
School of Computer Science, The University of Sydney(悉尼大学计算机学院);School of Electrical Engineering and Telecommunications, University of New South Wales(新南威尔士大学电气工程与电信学院)
Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
School of Software Technology, Zhejiang University(浙江大学软件技术学院);Zhejiang University(浙江大学);Hefei University of Technology(合肥工业大学);Institute of Fundamental and Transdisciplinary Research, Zhejiang University(浙江大学基础与交叉学科研究院);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江区)区块链与数据安全研究院);The State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Zhejiang Key Laboratory of Big Data Intelligent Computing(浙江省大数据智能计算重点实验室)
Protecting Bystander Privacy via Selective Hearing in Audio LLMs
VRAIN, Universitat Politècnica de València(VRAIN,瓦伦西亚理工大学);Department of Engineering, University of Cambridge(剑桥大学工程系);INGENIO (CSIC-Universitat Politècnica de València)(INGENIO(CSIC-瓦伦西亚理工大学))
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
Halıcıoğlu Data Science Institute, UC San Diego(哈里奇奥格卢数据科学研究所,加州大学圣地亚哥分校);Department of Computer Science and Engineering, UC San Diego(计算机科学与工程系,加州大学圣地亚哥分校);Department of Electrical Engineering, National Taiwan University(电气工程系,国立台湾大学);OpenAI
Operationalising the Right to be Forgotten in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments
Department of Mathematics(数学系);Munster Technological University(穆恩斯特技术大学);Department of Computer Science(计算机科学系)