Privacy Leakage in Language Models

Ask about this topic

Momentum

19 papers in the last four weeks, up 58% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 159

All topics
CardsList

  1. LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning

    Jul 2, 2026Matteo Boglioni, Thibault Rousset, Siva Reddy +2Privacy Leakage in Language ModelsMachine Unlearning

    Mila – Quebec Artificial Intelligence Institute · McGill University · McGill-NLP/LACUNA

  2. Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models

    Jul 1, 2026Mikołaj Słowikowski, Maciej Witold MajewskiDecoder-Only Language ModelsPrivacy Leakage in Language Models

    AGH University of Krakow, Faculty of Physics and Applied Computer Science, al. Mickiewicza 30, 30-059 Krakow, Poland

  3. Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed

    Jun 30, 2026Zhichao Fan, Zexin Zhuang, Yanhang LiMemorization in Language ModelsLLM Auditing

    University of Illinois Urbana-Champaign · Southern Methodist University · Northeastern University

  4. ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

    Jun 26, 2026Shijing Hu, Liang Liu, Zhu Meng +1Privacy AuditingTool-Use Evaluation

    Beijing University of Posts and Telecommunications, Beijing, 100876, China · Beijing Academy of Blockchain and Edge Computing, Beijing, 100085, China

  5. Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

    Jun 25, 2026Nada Lahjouji, Ashwin Gerard ColacoPrivacy Leakage in Language ModelsInformation Flow Control

    University of California, Irvine Irvine, California, USA

  6. Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

    Jun 23, 2026Yuanhe Zhao, Tianyu Zhang, Huafei Xing +3Retrieval-Augmented GenerationPrivacy Leakage in Language Models

    School of Control and Computer Engineering, North China Electric Power University, Beijing, 102206, China · Department of Computer & Information Science & Engineering, University of Florida, Gainesville, Florida, 32611, USA · NLP2CT Lab, Department of Computer and Information Science, University of Macau, Macao, 999078, Macao SAR +1

  7. GIF: Locally Sound Geometric Information Flow Control for LLMs

    Jun 22, 2026Adam Storek, Nikolaus Holzer, Zhuo Zhang +1Privacy Leakage in Language ModelsLLM Security

    Columbia University

  8. MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations

    Jun 22, 2026Elena Sofia Ruzzetti, Cornelius Emde, Sangdoo Yun +2Privacy Leakage in Language Models

    Parameter Lab · University of Oxford · NAVER AI Lab +1

  9. Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models

    Jun 22, 2026Yiran Zhu, Ziqi YangMembership Inference AttacksLLM Auditing

    Zhejiang University

  10. PrivacyAlign: Contextual Privacy Alignment for LLM Agents

    Jun 19, 2026Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3Reward ModelingPrivacy Leakage in Language Models

    University of Waterloo · †Work done during internship at ServiceNow AI Research · 2ServiceNow AI Research +2

  11. TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction

    Jun 17, 2026Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun +2Privacy-Preserving Language ModelsPrivacy Leakage in Language Models

    Dept. of Electrical Engineering, POSTECH · Grad. School of Artificial Intelligence, POSTECH · Grad. School of Metaverse, KAIST +1

  12. Unintended Effects of Geographic Conditioning in Large Language Models

    Jun 16, 2026Naz Col, David M. ChanPrivacy Leakage in Language ModelsLanguage Model Bias Evaluation

    University of California, Berkeley

  13. The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models

    Jun 15, 2026Chen Chen, Xiang Gao, Xianshun Wang +6Privacy-Preserving Language ModelsPrivacy Leakage in Language Models

    College of Computing and Data Science, Nanyang Technological University, Singapore · School of Cyber Science and Engineering, Wuhan University, China

  14. Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference

    Jun 15, 2026Alexander Yukhimchuk, Andrey Shulga, Mladen Kolar +1Privacy-Preserving Language ModelsLLM Inference

    MBZUAI · University of Southern California

  15. Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs

    Jun 15, 2026Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree +2Privacy Leakage in Language ModelsLLM Security

    UC Riverside · Riverside, California, USA · Queen’s University Belfast +2

  16. VLALeaks: Membership Inference Attacks against Vision-Language-Action Models

    Jun 13, 2026Xukun Luan, Jinyan Liu, Xuesong Li +4Membership Inference AttacksPrivacy Leakage in Language Models

    School of Computer Science and Technology, Beijing Institute of Technology · School of Computer Science and Engineering, Northeastern University · PRADA Lab, King Abdullah University of Science and Technology

  17. From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

    Jun 12, 2026Zixuan Gu, Xiaojun Ye, Yang LiuPrivacy-Preserving Language ModelsPrivacy Leakage in Language Models

    School of Software, Tsinghua University, Beijing, China · the Hong Kong Polytechnic University, Hongkong, China

  18. The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models

    Jun 10, 2026Chenyu Zhou, Qiliang Jiang, Shuning Wu +1Vision-Language ModelsAdversarial Attacks

    School of Engineering, Institute of Science Tokyo Tokyo, Japan · College of Control Science and Engineering, Zhejiang University Hangzhou, China · Department of Electrical and Computer Engineering, National University of Singapore Singapore, Singapore

  19. Advancing the State-of-the-Art in Empirical Privacy Auditing

    Jun 9, 2026Nicole Mitchell, Galen Andrew, Arun Ganesh +2Data LeakagePrivacy Auditing

    Google Research San Francisco, CA · Google Research Seattle, WA

  20. Alignment Defends LLMs from Property Inference Attacks

    Jun 8, 2026Pengrun Huang, Chhavi Yadav, Ruihan Wu +1LLM AlignmentPrivacy Leakage in Language Models

    University of California, San Diego · Carnegie Mellon University · Simons Institute, UC Berkeley

  21. Deployment-Time Memorization in Foundation-Model Agents

    Jun 8, 2026Lei, Chen, Guilin Zhang +8Persistent Memory for Language ModelsPrivacy Leakage in Language Models

    Rachel

  22. Clinically Grounded Privacy Evaluation of Medical LMs

    Jun 8, 2026Sasha Ronaghi, Sana Tonekaboni, Lena Stempfle +6Data LeakageMemorization in Language Models

    1Stanford University · 2Massachusetts Institute of Technology · 3American Board of Family Medicine

  23. SecureClaw: Clawing Back Control of LLM Agents

    Jun 8, 2026Yuhan Ma, Stefan SchmidData LeakageLLM Agent Security

    1TU Berlin

  24. Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

    Jun 8, 2026Bartłomiej Marek, Lorenzo Rossi, Vincent Hanke +4Privacy-Preserving Language ModelsMembership Inference Attacks

    CISPA Helmholtz Center for Information Security

  25. Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

    Jun 8, 2026Tiejin Chen, Pingzhi Li, Kaixiong Zhou +2Multimodal Large Language ModelsPrivacy Leakage in Language Models

    Arizona State University · University of North Carolina at Chapel Hill · North Carolina State University

  26. Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

    Jun 5, 2026Gonzalo Mancera, Daniel DeAlcala, Aythami Morales +3Membership Inference AttacksLLM Auditing

    BiometricsAI, Universidad Autonoma de Madrid, Spain · Department of Mathematics, Universidad de Las Palmas de Gran Canaria, Spain · Computer Engineering Department, Universidad Autonoma de Madrid, Spain

  27. Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2

    Jun 5, 2026Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez +3Membership Inference AttacksPrivacy Leakage in Language Models

    BiometricsAI, Universidad Aut´onoma de Madrid, Spain

  28. PromptPrint: Behavioral Biometrics Through Natural Language Prompting in LLMs

    Jun 4, 2026Shaiv Patel, Kartik Narayan, Vishal PatelBiometric IdentificationPrivacy Leakage in Language Models

    Johns Hopkins University, Baltimore, MD, USA

  29. LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

    Jun 4, 2026Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke PoechData LeakageMemorization in Language Models

    University of Southern Denmark

  30. When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents

    Jun 4, 2026Lingxiang Xu, Jiaoyun Yang, Min Hu +2Language Model Safety EvaluationPersistent Memory for Language Models

    †Hefei University of Technology · ‡Harvard Medical School