Privacy Leakage in Language Models

Follow this topic 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

Latest papers 159

All topics

What to Admit and How to Present: Governing Persistent Memory in LLM Agents
Oct 8, 2026Chang Liu, Deliang DingAgent Memory Management Persistent Memory for Language Models
Pazhou Laboratory Guangzhou, China
Sensitive-Topic Leakage Through LLM Routing Metadata: Measurement and Mitigation
Oct 7, 2026Teng-Ruei ChenPrivacy Leakage in Language Models LLM Routing
Krixvon, Taipei 100, Taiwan
Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII
Oct 5, 2026Alexandru Nazare, Agnese Profico, Nicolò Vania +6Multilingual Language Models Cross-Lingual Representation Alignment
Human-Centric ART, University of Rome Tor Vergata · Department of Computer Science, University of Luxembourg · Almawave Labs, Rome
AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search
Oct 4, 2026Jianing Wen, Tianshi LiPrivacy Leakage in Language Models AI Agent Security Benchmarks
Khoury College of Computer Sciences Northeastern University Boston, MA
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
Oct 4, 2026Shang Wang, Tianqing Zhu, Huajie Chen +3LLM Backdoor Attacks Model Extraction Attacks
School of Computer Science, University of Technology Sydney, Sydney, Australia · Faculty of Data Science, City University of Macau, Macau, China
The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching
Oct 1, 2026Alessandro Pegoraro, Daryan Merx, Phillip Rieger +1LLM Agent Security Privacy Leakage in Language Models
Technical University of Darmstadt · Graz University of Technology
OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents
Oct 1, 2026Taolin Zhang, Jiuheng Wan, Hanyu Wang +2Privacy Leakage in Language Models AI Agent Security Benchmarks
Hefei University of Technology · East China Normal University · Alibaba Cloud Computing
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
Sep 30, 2026Fahao Chen, Linkang Du, Jinhao Zhou +2LLM Inference Privacy Leakage in Language Models
Shandong University China · Xi’an Jiaotong University China · Waseda University Japan
PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration
Sep 29, 2026Dannong Wang, Yuran Zhang, Bian Sun +4Multi-Agent LLM Systems Privacy-Preserving Language Models
Institute of Artificial Intelligence, University of Central Florida · Department of Computer Science and Operations Research, Universit´e de Montr´eal · Department of Medicine, University of Central Florida
Audience-Bound Persistent Memory: Authorization Across the Memory Lifecycle
Sep 28, 2026Sibo LiuLLM Agent Memory Privacy Leakage in Language Models
Independent Researcher
"Nothing to See Here'': Unintended Disclosure through Revision Traces of LLM Deliverables
Sep 28, 2026Yage Zhang, Yukun Jiang, Yang ZhangPrivacy-Preserving Language Models LLM Auditing
CISPA Helmholtz Center for Information Security
EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents
Sep 28, 2026Fengzhou Sun, Yuan Zhang, Xintong Yu +1LLM Agent Memory Privacy Leakage in Language Models
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China
The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning
Sep 27, 2026Sae Furukawa, Alina OpreaSupervised Fine-Tuning Privacy Leakage in Language Models
Khoury College of Computer Sciences, Northeastern University
Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time
Sep 26, 2026Jacob Dineen, Silei Ren, Muhao Chen +2AI Agent Security Privacy Leakage in Language Models
Arizona State University · Cornell University · University of California, Davis +1
PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations
Sep 24, 2026Luciano MaldonadoLLM Auditing Privacy Leakage in Language Models
West Virginia University, Morgantown, WV, USA.
The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning
Sep 24, 2026Manit Baser, Aditya Nawal, Dinil Mon Divakaran +1Adversarial Attacks on LLMs Privacy Leakage in Language Models
National University of Singapore · A*STAR Institute of Advanced Intelligence and Computing, Singapore
GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation
Sep 18, 2026Zeyu Yan, Guanghao Zhou, Minghui Qiu +2Privacy Leakage in Language Models Machine Unlearning
East China Normal University, Shanghai, China · Unaffiliated
Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning
Sep 15, 2026Qingchen Yu, Shiying Duan, Xiaodong Li +5Privacy Leakage in Language Models Machine Unlearning
1Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University · School of Artificial Intelligence, Beihang University · Center for Applied Statistics, School of Statistics, Renmin University of China +1
RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
Sep 14, 2026Xingyu Lyu, Jiayimei Wang, Jianfeng He +3Privacy Leakage in Language Models RAG Security
University of Massachusetts Lowell, Lowell, MA 01854, USA · City University of Hong Kong, Kowloon, Hong Kong SAR, 999077, China · Virginia Tech, Blacksburg, VA 24061, USA +2
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
Sep 14, 2026Ahmed Sohair Khan, Estrid He, Chenglong Ma +2Privacy Auditing Privacy Leakage in Language Models
RMIT University, Melbourne, Australia
K-Bench: A Benchmark for LLM Unlearning in Agentic Deployments
Sep 11, 2026Guangsheng Yu, Yanna Jiang, Qin Wang +2LLM Agent Evaluation Privacy Leakage in Language Models
University of Technology Sydney, Australia · CSIRO, Australia
Privacy-Preserving Split Learning for Federated LLM Fine-Tuning
Sep 9, 2026Heng Jin, Chaoyu Zhang, Hexuan Yu +2Privacy-Preserving Language Models Split Federated Learning
Virginia Tech, Arlington, VA, USA
Extracting Forgotten Prompts from Targeted Unlearned Models
Sep 3, 2026Au Ashley Hoi-Ting, Meghdad Kurmanji, William F. Shen +2Privacy Leakage in Language Models LLM Unlearning
University of Warwick · University of Cambridge
Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study
Sep 1, 2026Arpan Kumar MahapatraMCP Security LLM Agent Security
Embedded Conditional Independence Tests for Large Language Model Generated Text with an Application to German Parliament Speeches
Sep 1, 2026Marco Simnacher, Georg Keilbar, Benjamin König +2LLM Evaluation Privacy Leakage in Language Models
Chair of Statistics Humboldt-Universität zu Berlin Spandauer Str. 1, 10178 Berlin, Germany · Chair Digital Health & Machine Learning Hasso-Plattner-Institut for Digital Engineering Prof.-Dr.-Helmert-Straße 2-3, 14482 Potsdam, Germany
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Sep 1, 2026Shengfang Zhai, Leo Marchyok, Yuling Shi +4Memorization in Language Models Membership Inference Attacks
National University of Singapore · Oregon State University · Shanghai Jiao Tong University +1
Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
Sep 1, 2026Miso Kim, Georu Lee, Seungwon Jeong +1Privacy Leakage in Language Models Machine Unlearning
Dongguk University-Seoul
Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization
Aug 31, 2026Dishu Yang, Jingjing Liu, Jize LiLLM Alignment Memorization in Language Models
Khoury College of Computer Sciences Northeastern University San Jose, USA · Department of Electrical Engineering and Computer Sciences University of California, Berkeley Berkeley, USA · Department of Economics Boston University Boston, USA
On the Recoverability of Private Information Unlearning in Large Language Models
Aug 30, 2026Shicheng Hu, Runzhi Tian, Ziqiao Wang +1LLM Auditing Privacy Leakage in Language Models
University of Illinois Urbana-Champaign · University of Ottawa · Tongji University
Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs
Aug 13, 2026Saleh Almohaimeed, Saad Almohaimeed, Mousa Jari +2Retrieval-Augmented Generation Privacy Leakage in Language Models
College of Applied Computer Science, King Saud University, Riyadh, Saudi Arabia

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

What to Admit and How to Present: Governing Persistent Memory in LLM Agents

Chang Liu, Deliang Ding

Pazhou Laboratory Guangzhou, China

Agent Memory Management Persistent Memory for Language Models LLM Agent Safety Privacy Leakage in Language Models

Open paper AskPDF arXiv

Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decisions: admission, which determines what recalled information enters the working context, and presentation, which determines how admitted information is expressed. We implement two inference-time designs without retraining: factor-compiled admission (FC), which assesses whole memory entries, and permission-semantic admission (PS), which decomposes entries into typed units; both translate adjudicated attributes into eligibility decisions via deterministic policies. We evaluate on a four-backbone development suite and an external benchmark with four tasks of 300 samples each. Relative to verbatim injection, FC and PS reduce pooled judge-assessed failure rates on the external benchmark by 6.7 and 8.8 percentage points (p = 2.7e-7 and 4.1e-12), and development-set cross-domain leakage falls by up to 29.5 percentage points. A query-conditioned gating baseline shows no significant change in objective-fact failure or pooled failure. Under matched admission budgets, PS outperforms random and relevance-based selection on external objective-fact judgment after Holm correction. Holding presentation fixed, tightening admission cuts cross-domain failure by a further 17.5 percentage points (p = 1.6e-4); in contrast, no comparison between two renderings of identical adjudicated outputs survives multiple-comparison correction. Both designs increase personalization failures, and PS misses the preregistered improvement and personalization-preservation criteria. These results support evaluating admission and presentation separately: selection quality provides task-specific safety gains, while preserving beneficial memory use remains unresolved.

Momentum

Related topics

Latest papers 159