Privacy Risks of General-Purpose Language Models

Cited by (192)

Items 101–192 of 192

1. 1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
   Stephen Meisenbacher, Maulik Chevli, Florian Matthes · 2024 · ACM International Workshop on Security and Privacy Analytics (IWSPA)
2. Model Extraction and Defenses on Generative Adversarial Networks
   Hailong Hu, Jun Pang · 2021 · arXiv (Cornell University)
3. Quantifying and Mitigating Privacy Risks of Contrastive Learning
   Xinlei He, Yang Zhang · 2021 · arXiv (Cornell University)
4. InvBERT: Text Reconstruction from Contextualized Embeddings used for Derived Text Formats of Literary Works
   Johannes Höhmann, Achim Rettinger, Kai Kugler · 2021 · arXiv (Cornell University)
5. Human-inspired Perspectives: A Survey on AI Long-term Memory
   He, Zihong, Lin, Weizhe, Zheng, Hao, Zhang, Fan, Jones, Matt W., Aitchison, Laurence, Xu, Xuhai, Liu, Miao, Kristensson, Per Ola, Shen, Junxiao · 2024 · arXiv
6. Broken Bags: Disrupting Service Through the Contamination of Large Language Models With Misinformation
   Yonghua Mo, Maoyang Tang, Ruohan Lin, Bohao Zhou, Xiaojian Li · 2025 · IEEE Access
7. Natural Language Processing and Large Language Models
   Gordon C. Wong, Kevin C. Chung · 2025 · Hand Clinics
8. LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data
   Stephen Meisenbacher, Alexandra Klymenko, Florian Matthes · 2025 · Proceedings of the 2025 Workshop on Human-Centered AI Privacy and Security
9. Analyzing sensitive information leakage in trajectory embedding models
   Jiaxin Ding, Shichuan Xi, Kailong Wu, Pan Liu, Xinbing Wang, Chenghu Zhou · 2022 · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS)
10. Data Provenance via Differential Auditing
    Xin Mu, Ming Pang, Feida Zhu · 2023 · IEEE Transactions on Knowledge and Data Engineering
11. Federated Learning with Local Openset Noisy Labels
    Zonglin Di, Zhaowei Zhu, Xiaoxiao Li, Yang Liu · 2024 · Lecture notes in computer science
12. WhyGen
    Weixiang Yan, Yuanchun Li · 2022 · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)
13. Differential Privacy in HyperNetworks for Personalized Federated Learning
    Vaisnavi Nemala, Phung Lai, NhatHai Phan · 2023 · ACM International Conference on Information and Knowledge Management (CIKM)
14. TextMixer: Mixing Multiple Inputs for Privacy-Preserving Inference
    Xin Zhou, Yi Yu Lu, Ruotian Ma, Tao Gui, Qi Zhang, Xuanjing Huang · 2023 · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
15. Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Text
    Stephen Meisenbacher, Florian Matthes · 2024 · International Conference on Availability, Reliability and Security (ARES)
16. OpenBA: an open-sourced 15B bilingual asymmetric Seq2Seq model pre-trained from scratch
    Juntao Li, Zecheng Tang, Yuyang Ding, Pinzheng Wang, Pei Guo, Wangjie You, Dan Qiao, Chenyu Wang, Wenliang Chen, Guohong Fu et al. · 2025 · Science China Information Sciences
17. Digital Privacy Under Attack: Challenges and Enablers
    Baobao Song, Shiva Raj Pokhrel, Mengyue Deng, Qiujun Lan, Robin Doss, Tianqing Zhu, Gang Li · 2025 · ACM Computing Surveys
18. Fingerprinting Fine-tuned Language Models in the Wild
    Nirav Diwan, Tanmoy Chakraborty, Zubair Shafiq · 2021 · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
19. Cloud or On-Premise? A Strategic View of Large Language Model Deployment
    Zhike Zhang, Jiaqi Shi, Shaojie Tang · 2025 · SSRN Electronic Journal
20. Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks
    Antonios Tragoudaras, Theofanis Aslanidis, Emmanouil Georgios Lionis, M. González, Panagiotis Eustratiadis · 2025 · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
21. Privacy considerations for LLMs and other AI models: an input and output privacy approach
    Zixin Nie, Leena Dave, Rashonda Lewis · 2025 · Frontiers in Communications and Networks
22. On the Promises and Challenges of AI-Powered XR Glasses as Embodied Software
    Ruizhen Gu, Jingqiong Zhang, José Miguel Rojas, Donghwan Shin · 2025 · ACM International Conference on AI-Powered Software (AIware)
23. Data protection in the era of large language models: challenges and opportunities
    Zvinodashe Revesai, Colletor Tendeukai Chipfumbu · 2026 · AI and Ethics
24. From Language Models to Agentic AI: A Survey of Autonomous, Action-Enabled, and Collaborative LLM Agents
    Sparsh Bajoria -, Sumit Ranjan, Adhitya M, Vineet Suri, Vikas Hassija, Vinay Chamola, Amir Hussain · 2026 · Cognitive Computation
25. WhyGen
    Weixiang Yan, Yuanchun Li · 2022 · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)
26. Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcare
    Hyejun Jeong, Tai‐Myoung Chung · 2022 · Communications in computer and information science
27. Driving Context into Text-to-Text Privatization
    Stefan Arnold, Dilara Yesilbas, Sven Weinzierl · 2023 · Workshop on Trustworthy Natural Language Processing (TrustNLP)
28. InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning
    Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Minlie Huang · 2023 · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
29. Exploring Advanced Methodologies in Security Evaluation for Large Language Models
    Jun Huang, Jiawei Zhang, Qi Wang, Weihong Han, Yanchun Zhang · 2024 · Communications in computer and information science
30. How 6G and AI Can Reshape the Future of Electric Systems
    Aleksandr Zavodovski, Farid Hamzeh Aghdam, Antonio Caló, Rashid Dehkordi, Petr Štěpánek, Mehdi Rasti, Éva Pongrácz, Petri Ahokangas · 2024 · IEEE International Conference on Environment and Electrical Engineering and IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)
31. Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities
    Xi Li, Chen Wu, Jiaqi Wang · 2025 · International Joint Conference on Neural Networks (IJCNN)
32. Private Information Leakage in LLMs
    Beat Buesser · 2024 · Springer eBooks
33. A Privacy-Preserving Framework for Medical Chatbot Based on LLM with Retrieval Augmented Generation
    Yufei Li, Chunshan Li, Zecheng Wang, Dianbo Sui, Jianen Yan · 2024 · Lecture notes in computer science
34. Preserving Privacy During Reinforcement Learning With AI Feedback
    David Gao, Ian J. Miller, Ali Ataeemh Allami, Dan Lin · 2024 · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)
35. Financial Inclusion and Large Language Models
    Peterson K Ozili, Kingsley Isitua Obiora, Chinwendu Onuzo · 2025 · Advances in computational intelligence and robotics book series
36. Defense Against Syntactic Textual Backdoor Attacks With Token Substitution
    Xianwen He, Xinglin Li, Yao Li, Minhao Cheng · 2025 · IEEE Transactions on Information Forensics and Security
37. Can Personal Health Information Be Secured in LLM? Privacy Attack and Defense in the Medical Domain
    Yujin Kang, Eunsun Kim, Yoon-Sik Cho · 2025 · ACM SIGSAC Conference on Computer and Communications Security (CCS)
38. Adaptive Feature Representation Learning for Privacy-Fairness Joint Optimization
    Chao Ma, Mingkai Dai, Zhibo Guan, Zi Ye, Yikai Hou, Xiaoyu Wang, Hai Huang · 2025 · Applied Sciences
39. Comparing Reconstruction Attacks on Pretrained Versus Full Fine-tuned Large Language Model Embeddings on Homo Sapiens Splice Sites Genomic Data
    Reem Al-Saidi, Erman Ayday, Ziad Kobti · 2025 · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
40. ModelFreeUP: Attacking Sparse Network Monitoring via Model-Free Universal Adversarial Perturbation
    Ruotian Xie, Kun Xie, Jiazheng Tian, Jing Wang, Jigang Wen, Yang Xu, Guangxing Zhang, Wei Liang, Gaogang Xie · 2026 · IEEE Transactions on Networking
41. Small Is Beautiful: A Practical and Efficient Log Parsing Framework
    Minxing Wang, Yintong Huo · 2026 · Proceedings of the ACM on software engineering.
42. Adversarial for Good – Defending Training Data Privacy with Adversarial Attack Wisdom
    Shengyuan Pang, Yanjiao Chen, Jiangyi Deng, Jialin Wu, Yijie Bai, Wenyuan Xu · 2024 · IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom)
43. Privacy-preserving word vectors learning using partially homomorphic encryption
    Shang Ci, Sen Hu, Donghai Guan, Çetin Kaya Koç · 2025 · Journal of Information Security and Applications
44. Efficient and Deployable Knowledge Infusion for Open-World Recommendations via Large Language Models
    Yunjia Xi, Weiwen Liu, Jianghao Lin, Muyan Weng, Xiaoling Cai, Hong Chun Zhu, Jieming Zhu, Bo Chen, Ruiming Tang, Yong Hai Yu et al. · 2025 · ACM Transactions on Recommender Systems
45. Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting
    Stephen Meisenbacher, Chaeeun Joy Lee, Florian Matthes · 2024 · ACM Conference on Data and Application Security and Privacy (CODASPY)
46. POSTER: When Models Speak Too Much: Privacy Leakage on Large Language Models
    MingJun Zhang, Mahrokh Abdollahi, Thilina Ranbaduge, Ming Ding · 2025 · ACM Asia Conference on Computer and Communications Security (ASIA CCS)
47. User-Entity Differential Privacy in Learning Natural Language Models
    Phung Lai, NhatHai Phan, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios · 2022 · IEEE International Conference on Big Data (BigData)
48. Proceedings of the Fourth Workshop on Privacy in Natural Language Processing
    2022
49. Opportunities and Challenges in Applying Machine Learning for Access Control
    Sora Nakamura · 2023
50. Integrity and privacy in adversarial machine learning
    Matthew Jagielski · 2021 · Digital Repository Service (Northeastern University)
51. Opportunities and Challenges in Applying Machine Learning for Access Control
    Sora Nakamura, Yuto Tanaka · 2023
52. Disentangling the Linguistic Competence of Privacy-Preserving BERT
    Stefan Arnold, Nils Kemmerzell, Annika Schreiner · 2023 · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)
53. Client Availability Aware Privacy-Preserving Federated Learning for Language Models
    Sheng Yun, Md Zakirul Alam Bhuiyan, Md. Taufiq Al Hasib Sadi · 2023 · International Conference on Computer and Information Technology (ICCIT)
54. Privacy in Federated Learning Natural Language Models
    Phung Lai, Cesar Ariel Pinto · 2024 · Springer optimization and its applications
55. Adversarial Reconstruction of Trajectories: Privacy Risks and Attack Models in Trajectory Embedding
    Haochen Han, Shuaiyu Yang, Jiaxin Ding, Luoyi Fu, Xinbing Wang, Chenghu Zhou · 2024 · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS)
56. Invited Paper: Security and Privacy in Large Language and Foundation Models: A Survey on GenAI Attacks
    Giuseppe Francesco Italiano, Alessio Martino, Giorgio Piccardo · 2024 · Lecture notes in computer science
57. The Colossal Defense: Security Challenges of Large Language Models
    Sourav Maity, Jatin Arora · 2024 · IEEE Delhi Section Conference (DELCON)
58. A Quantitative Privacy Evaluation Method Based on Tsallis Entropy for Trustworthy Data Sharing
    Shudan Yang, Pierluigi Plebani · 2025 · Lecture notes in computer science
59. Large Language Models (LLMs) as Search Engine Alternatives for Health Information Seeking Among Patients with Severe Congenital Scoliosis and Families: A Qualitative Phenomenological Investigation (Preprint)
    Tao Chen, Qiang Li, Deng Zhao, Wenjing Zhang, Yong Li, Jin-dong Yang, Chun Pu, Qiang Fu · 2024 · JMIR Formative Research
60. Goalie: Defending Against Correlated Value and Sign Encoding Attacks
    Rongfei Zhuang, Ximing Fu, Chuanyi Liu, Peiyi Han, Shaoming Duan · 2025 · Entropy
61. Mobile AI-Generated Content Data Sharing Privacy-Preserving Scheme for Logistics IoT in 6G Era
    Kunchang Li, Rui-Yao Wang, Hao Wang, Yichun Wang · 2025 · Communications in computer and information science
62. Sentence Embedding Generation Method for Differential Privacy Protection
    Yangyang Liu, Wanqi Wang, Jingyu Hua · 2025 · Lecture notes in computer science
63. Many-Shot Regurgitation Prompting
    Shashank Sonkar, N.-S. Liu, Richard G. Baraniuk · 2025 · Lecture notes in computer science
64. Data safety: attacks
    Yu–Gang Jiang, Xingjun Ma, Zuxuan Wu · 2025 · Elsevier eBooks
65. Bibliography
    2025 · Elsevier eBooks
66. Securing social network user data in large language model deployments: challenges and best practices
    Nasir Ahmad Jalali, Chen Hongsong · 2025 · Cluster Computing
67. Research on Data Integrity Protection and Encryption Technologies for Large Language Models
    Binyuan Yan, Qiucheng Ban, Lu Xiang · 2025 · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA)
68. Tyche: Probabilistic Selection over Encrypted Data for Generative Language Models
    Lars Wolfgang Folkerts, Nektarios Georgios Tsoutsos · 2025 · ACM Transactions on Internet Technology
69. RLMI: A Black-Box Model Inversion Attack Method Against Large Language Models for Text Classification
    Yuxin Xie, Ying Gao · 2025 · Chinese Journal of Electronics
70. Reinforcement Learning-Guided Large Language Model Fine-Tuning for Privacy-Preserving Text Rewriting
    Zhan Shi, Yefeng Yuan, Liang Cheng, Yuhong Liu · 2025 · ACM/IEEE Symposium on Edge Computing (SEC)
71. Ethical Analysis of Large Language Models: A Comparison of GPT, DeepSeek, Claude, Gemini, LLaMA, and Qwen
    Leonidas Boutsikaris, Spyros E. Polykalas · 2025 · IEEE International Symposium on Technology and Society (ISTAS)
72. A Secure and Effective Framework for Key Concept Mining from Educational Content Using Large Language Models
    Ashika Sameem Abdul Rasheed, Mohammad Mehedy Masud · 2025 · IEEE International Conference on Application of Information and Communication Technologies (AICT)
73. LLM-Augmented Sensor Fusion for Urban Socioeconomic Monitoring: A Cyber–Physical–Social Systems Perspective
    Hui Xie, Hui Cao, Hongkai Zhao · 2025 · Systems
74. ProSan: Utility-Based Prompt Privacy Sanitizer
    Zhili Shen, Zihang Xi, Ying He, Wei Tong, Jingyu Hua, Sheng Zhong · 2026 · IEEE Transactions on Information Forensics and Security
75. Research on Key Technologies for Data Security Protection Based on Large Models
    Wen Ting Jiang, Zhimin Wu, Chen Chen · 2025 · International Communication Engineering and Cloud Computing Conference (CECCC)
76. Combining differential privacy and homomorphic encryption for privacy-preserving collaborative machine learning
    Arnaud Grivet Sébert · 2023
77. Information Extraction from Electronic Health Records : Studies on temporal ordering, privacy and environmental impact
    Nesrine Bannour · 2023 · theses.fr (ABES)
78. A Systematic Study of Security and Privacy in Large Language Models
    Bingyu Liu · 2026 · International Symposium on Digital Forensics and Security (ISDFS)
79. Your Permission Leaks My Data: Second-Hand Privacy Harms in LLM Agents
    Minje Kim, Keeheon Lee · 2026 · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA)
80. How Private Are Genomic Embeddings? Assessing and Mitigating Reconstruction Attacks on Transformer-Based DNA Language Models Embeddings
    Reem Al-Saidi · 2026 · IEEE International Conference on Data Engineering Workshops (ICDEW)
81. Rotation Key Scheduling: Temporal Invalidation of Alignment-Based Embedding Inversion in RAG Systems
    SeungSoo Baek · 2026 · SSRN Electronic Journal
82. PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration
    Yi Liu, Weixiang Han, Chengjun Cai, Xingliang Yuan, Ce Wang · 2026 · IEEE Conference on Computer Communications (INFOCOM)
83. Digital Vulnerability and AI-Powered Legal Services
    giovanni chieco · 2025 · Springer eBooks
84. Optimizing MLaaS Platform Selection: A Performance, Cost, and Security Analysis of AWS, Google Cloud, and Microsoft Azure
    Puhiza ISENI, Jaumin Ajdari, Xhemal Zenuni, Mentor Hamiti · 2026 · International Convention on Information and Communication Technology, Electronics and Microelectronics
85. A Methodology for Analysing Coding Bugs for LLMs and SAST
    Madjid Tehrani, William Johnston Buchanan, Eldar Gunter Sultanow, Mahkame Houmani, Christel H. Djaha Fodja, Mouad Lemoudden · 2026 · Lecture notes in networks and systems
86. Large Language Model-Based Approaches in Electronic Design: A Brief Review
    Levente Kovács, Zoltán Tafferner, Attila Géczy · 2026 · International Spring Seminar on Electronics Technology
87. Where LLM-Assisted Cyberattacks Break Down: A Stage-Level Analysis of Workflow Execution Boundaries
    Gabby Campos, Tam Nguyen, Chetraj Pandey, Prashnna Gyawali, Robin Chataut · 2026 · Lecture notes in computer science
88. Addressing Dynamic and Socio-Technical Privacy Risks: A Position Paper on System Dynamics for Privacy-Risk Assessment
    Rokhman Fauzi, Jaka Sembiring, I Gusti Bagus Baskara Nugraha, Basuki Rahmad · 2026 · International Conference on Enterprise and Industrial System (ICOEINS)
89. Vulnerabilities in the Tower: Assessing Embedding Nucleotide Inference Risks in Hybrid CNN-Transformer Genomic Large Language Models (HgLLMs)
    Reem Al-Saidi, Erman Ayday, Ziad Kobti · 2026 · IEEE International Conference on Healthcare Informatics (ICHI)
90. PI-SAFE: Practical Privacy-Preserving LLM Inference With Adversarial Fine-Tuning for Optimized Utility
    Wentao Zhong, Yuting Li, Dicong Yu, Wenhua Wang, Qin Liu, Lei Xue, Zhiyong Yu, Jun Zhang, Weijia Jia B, Tian Wang · 2026 · IEEE Transactions on Information Forensics and Security
91. Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaboration
    Shuaifan Jin, Xiaoyi Pang, Zhibo Wang, He Wang, Jiacheng Du, Jiahui Hu, Kui Ren · 2026 · IEEE Transactions on Networking
92. SPARAG: Differentially private Retrieval-Augmented Generation via sampling and aggregation
    Yinchi Ge, Hui Zhang, Xuyao Zhai, Shenghao Jin, Haijun Yang · 2026 · Knowledge-Based Systems