User Attribute Inference Attacks

Latest papers

10 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
Oct 17, 2026Qishun Yang, Shu Yang, Difei Xu +2Memory Agent Benchmarks Data Leakage
University of Massachusetts Boston · King Abdullah University of Science and Technology · Provable Responsible AI and Data Analytics Lab
Reading Is Not Leaking: Local, Auditable Measurement and Reduction of Inference Exposure from Public Footprints
Sep 26, 2026Mahmudul Faisal Al AmeenUser Attribute Inference Attacks Privacy Leakage in Language Models
Independent researcher France
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
Sep 11, 2026Ahmed Sohair Khan, Estrid He, Chenglong Ma +2Privacy Auditing Privacy Leakage in Language Models
RMIT University, Melbourne, Australia
Attribute Inference from Interactive Targeted Ads
Jun 13, 2026Peihao LiPrivacy Auditing Adversarial Attacks
Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models
Jun 8, 2026Jianwei TaiData Leakage Adversarial Attacks
School of Internet, Anhui University
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
Jun 6, 2026Steven Golob, Sikha Pentyala, Martine De CockPrivacy Auditing Adversarial Attacks
School of Engineering and Technology, University of Washington Tacoma, Tacoma, WA, USA · Department of Mathematics, Computer Science, and Statistics, Ghent University, Gent, Belgium
The Impact of Temporal Granularity on Socio-Demographic Inference from Household Load Profiles
Jun 2, 2026Dejan Radovanovic, Maximilian Schirl, Andreas Unterweger +1Time Series Classification User Attribute Inference Attacks
Center for Secure Energy Informatics, Salzburg University of Applied Sciences, Puch bei Hallein, Austria · Paris Lodron University of Salzburg, Salzburg, Austria
Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies
May 19, 2026Yasmine HayderGraph Representation Learning Adversarial Attacks
PETSCRAFT · LIFO, INSA CVL, Univ. Orléans, Inria, France
From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists
May 6, 2026Stefano Cecconello, Mauro Conti, Luca Pajola +2User Attribute Inference Attacks Privacy-Preserving ML
University of Padova, Italy · Örebro University, Sweden · Spritz Matter, Italy
Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage
Mar 25, 2026Faiz Taleb, Ivan Gazeau, Maryline LaurentUser Attribute Inference Attacks Membership Inference Attacks
EDF SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France · EDF, 91120 Palaiseau, France · SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris

Oct 17, 2026J/K move · Enter open · S save

Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin

Qishun Yang, Shu Yang, Difei Xu, Di Wang+1

University of Massachusetts Boston · King Abdullah University of Science and Technology · Provable Responsible AI and Data Analytics Lab

Memory Agent Benchmarks Data Leakage Long-Term Conversational Memory User Attribute Inference Attacks Memory Management for LLM Agents

Open paper AskPDF arXiv

To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions. Reusing such memories can lead an agent to state a sensitive relation while completing an ordinary task that does not require it. The relation to protect and the combination of clues that reveal it may remain hidden at memory write time, when later records and tasks are still unknown. In this paper, we introduce MemJoin, a privacy benchmark of 288 synthetic analysis cases in which the complete history entails a sensitive relation, but every individual session is insufficient. We evaluate six memory systems with the same answer-generating model, alongside full-history and no-history controls. Each system writes and updates memories in session order and later retrieves context for an ordinary task, while target annotations remain with the evaluator. We separately check which target attribute values appear in stored records and retrieved context, and whether the final answer states the complete, person-linked relation. In a separate paired test on a prespecified subset, removing shared identifiers and other connecting clues can change complete-relation output while all checked target attribute values remain visible. These findings show why checking attribute visibility alone is insufficient to evaluate what records from different sessions reveal together.