Privacy Auditing

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 58

All topics

Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI
Jun 8, 2026Jonghyun Chung, Sanket BadhePrivacy Auditing AI Accountability
Google
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
A Large-Scale Per-Speaker Analysis of Re-identification Risk in Speech Anonymization
Jun 5, 2026Orane Dufour, Paul Magron, Mickael Rouvier +1Privacy Auditing Speech Processing
Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France · LIA, Avignon University, F-84911 Avignon, France
What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media
Jun 5, 2026Zifan Peng, Yini Huang, Aiwen Lu +7Social Media Analysis Data Leakage
The Hong Kong University of Science and Technology (Guangzhou) · Wuhan University
Bayesian Membership Privacy for Graph Neural Networks
Jun 2, 2026Sinan Yıldırım, Megha KhoslaPrivacy Auditing Graph Neural Networks
Faculty of Engineering and Natural Sciences Sabancı University Istanbul, Turkey · Intelligent Systems Department Delft University of Technology (TU Delft) Delft, The Netherlands
LLM-as-a-Discriminator: When Synthetic Tables Still Look Real
Jun 1, 2026Manel Slokom, Malek Slokom, Thierno KantePrivacy Auditing Tabular Data Synthesis
Vrije Universiteit, Amsterdam · Equativ, Paris · EDICIA, Nantes
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
May 29, 2026Mingxuan Zhang, Jiahui Han, Dadi Guo +5Data Leakage Privacy Auditing
Shanghai Artificial Intelligence Laboratory · Southeast University
A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
May 28, 2026Ding Chen, Xinwen Cheng, Xuyang Zhong +3Privacy Auditing Membership Inference Attacks
City University of Hong Kong · Shanghai Jiao Tong University · denotes the correspondence author.
Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run
May 26, 2026Mathieu Dagréou, Aurélien BelletPrivacy Auditing Membership Inference Attacks
PreMeDICaL team, Inria · Idesp, Inserm, Univ. de Montpellier
On Reliability of Membership Inference Vulnerability Evaluation
May 25, 2026Joonas Jälkö, Gauri Pradhan, Ossi Räisä +1Data Leakage Privacy Auditing
University of Helsinki, Finland · CISPA Helmholtz Center for Information Security, Germany
Unlocking Apple's Private Cloud Compute: An Analysis of Privacy-Preserving Artificial Intelligence
May 22, 2026Yannik Dittmar, Marvin Jerome Stephan, Thomas Völkl +2Privacy Auditing Privacy-Preserving Language Models
Hasso Plattner Institute, University of Potsdam Potsdam, Germany · TU Darmstadt, Secure Mobile Networking Lab Darmstadt, Germany · TU Darmstadt, Secure Mobile Networking Lab, Darmstadt, Germany +1
Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning
May 21, 2026Benjamin D. Kim, Lav R. Varshney, Daniel AlabiPrivacy Auditing Black-Box Model Auditing
University of Illinois Urbana-Champaign · 1Massachusetts Institute of Technology · Brook University
Auditing Privacy in Multi-Tenant RAG under Account Collusion
May 19, 2026Florian A. D. BurnatData Leakage Privacy Auditing
University of Bath, Bath, UK.
Privacy Evaluation of Generative Models for Trajectory Generation
May 14, 2026Stavros Bouras, Ioannis Kontopoulos, Chiara Pugliese +5Privacy Auditing Trajectory Generation
School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece · Institute of Informatics and Teletematics, National Research Council (CNR), Pisa, Italy · Institute of Information Science and Technologies, National Research Council (CNR), Pisa, Italy
VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection
May 11, 2026Xiaobin Hu, Enpu Zuo, Lanping Hu +7Privacy Auditing Privacy-Preserving ML
National University of Singapore · Australian National University · The University of New South Wales +1
Differentially Private Auditing Under Strategic Response
May 8, 2026Florian A. D. BurnatPrivacy Auditing Algorithmic Auditing
University of Bath
Addressing Labelled Data Scarcity: Taxonomy-Agnostic Annotation of PII Values in HTTP Traffic using LLMs
May 7, 2026Thomas Cory, Axel KüpperPrivacy Auditing LLM-Assisted Annotation
Technische Universität Berlin
Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption
May 1, 2026Gaoyi Chen, Minghao Li, Weishi Shi +4Data Leakage Privacy Auditing
Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA · Department of Electrical Engineering, University of North Texas, Denton, TX, USA
Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing
Apr 27, 2026Antony RowstronPrivacy Auditing AI Agent Auditing
Advanced Research and Invention Agency (ARIA) London, UK
PrivSTRUCT: Untangling Data Purpose Compliance of Privacy Policies in Google Play Store
Apr 24, 2026Bhanuka Silva, Anirban Mahanti, Aruna Seneviratne +1Privacy Auditing Document Information Extraction
The University of Sydney, Australia · University of New South Wales, Australia
Subject-level Inference for Realistic Text Anonymization Evaluation
Apr 23, 2026Myeong Seok Oh, Dong-Yun Kim, Hanseok Oh +6Privacy Auditing
Tscientific, South Korea · Soongsil University, South Korea · Yonsei University, South Korea +1
Tight Auditing of Differential Privacy in MST and AIM
Apr 20, 2026Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan KulynychPrivacy Auditing Synthetic Data Generation
1UCL · 2SAS · 3Lausanne University Hospital
VeriX-Anon: A Multi-Layered Framework for Mathematically Verifiable Outsourced Target-Driven Data Anonymization
Apr 14, 2026Miit Daga, Swarna Priya RamuPrivacy Auditing Privacy-Preserving ML
School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, 632014, Tamil Nadu, India
Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
Mar 23, 2026Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna +3VLM Evaluation Privacy Auditing
University of Southern California, Los Angeles CA 90089, USA · Meta Superintelligence Labs · Amazon AGI
Voice Privacy from an Attribute-based Perspective
Mar 19, 2026Mehtab Ur Rahman, Martha Larson, Cristian Tejedor-GarciaPrivacy Auditing Speech Processing
Centre for Language Studies · Institute for Computing and Information Sciences
Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective
Jan 30, 2026Georgi Ganev, Emiliano De CristofaroPrivacy Auditing Synthetic Tabular Data Generation
UCL · SAS · UC Riverside
Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness
Oct 13, 2025Sleem Abdelghafar, Maryam Aliakbarpour, Christopher JermaineData Leakage Privacy Auditing
Rice University Houston, USA
Optimizing Canaries for Privacy Auditing with Metagradient Descent
Jul 21, 2025Matteo Boglioni, Terrance Liu, Andrew Ilyas +1Privacy Auditing Differentially Private Stochastic Gradient Descent
Carnegie Mellon University · Stanford Statistics

Jun 8, 2026, cs.CRJ/K move · Enter open · S save

Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI

Jonghyun Chung, Sanket Badhe

Google

Privacy Auditing AI Accountability AI Governance On-Device Inference

Open paper AskPDF arXiv

As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally. A local assistant may assemble email, calendar entries, files, screenshots, notifications, and app intents; retain embeddings or summaries; invoke tools; emit telemetry; or route difficult requests to cloud infrastructure. Local inference reduces some exposure, but it answers only one question: where computation occurs. It does not answer who may assemble context, what derived state persists, which actions are authorized, or how updates change the system's authority. We develop an OS-centered privacy framework for on-device AI that treats privacy as an institutional accountability problem rather than a deployment attribute. The framework specifies a threat model, a six-part privacy risk taxonomy, privacy-by-architecture controls, and a four-level audit rubric. We demonstrate the rubric through a documentation-bounded comparison of Apple Intelligence/Foundation Models, Android AICore/Gemini Nano, and Microsoft Recall. Meaningful privacy in on-device AI depends on constrained information flow, bounded authority, visible user control, and auditable governance across the operating-system lifecycle.

Momentum

Related topics

Latest papers 58