Privacy

Follow this topic Ask about this topic

Momentum

26 papers in the last four weeks, up 13% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 275

All topics

Tight Auditing of Differential Privacy in MST and AIM
Apr 20, 2026Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan KulynychStandard Differential-Privacy Privacy
1UCL · 2SAS · 3Lausanne University Hospital
Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion
Apr 19, 2026Ou Wu1B Parameters Privacy
HIAS, University of Chinese Academy of Sciences, Hanzhou, China, 310000
Understanding U.S. Users' Security and Privacy Transparency Needs for Consumer-Facing Generative AI
Apr 19, 2026Jiaxun Cao, Yu Dong, Chunxi Zhan +3Transparency Interaction Design
Duke University · Duke Kunshan University · Google
PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences
Apr 18, 2026Bo Ma, Weiqi Yan, Jinsong WuPrivacy Privacy-Utility Trade-Offs
Resideo Technologies Inc., Scottsdale, Arizona, USA · Auckland University of Technology, Auckland, New Zealand · Guilin University of Electronic Technology, Guilin, China
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Apr 17, 2026Andreea-Elena Bodea, Stephen Meisenbacher, Florian MatthesAnonymization Retrieval-Augmented Generation Pipelines
Technical University of Munich · School of Computation, Information and Technology · Garching, Germany
CAMP: Cumulative Agentic Masking and Pruning for Privacy Protection in Multi-Turn LLM Conversations
Apr 16, 2026Aman PanjwaniPrivacy Multi-Turn Large Language Model Conversations
Independent Researcher
Decoupling Identity from Utility: Privacy-by-Design Frameworks for Financial Ecosystems
Apr 16, 2026Ifayoyinsola Ibikunle, Tyler Farnan, Senthil Kumar +1Synthetic Data Anonymization
Capital One
Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
Apr 10, 2026Joanna KomorniczakSynthetic Tabular Data Synthetic Data
Department of Systems and Computer Networks, Wrocław University of Science and Technology
Designing Privacy-Preserving Visual Perception for Robot Navigation Based on User Privacy Preferences
Apr 7, 2026Xuying Huang, Sicong Pan, Delphine Reinhardt +1Robot Navigation Visual Perception
Humanoid Robots Lab, University of Bonn, the Lamarr Institute for Machine Learning and Artificial Intelligence and the Center for Robotics, Bonn, Germany · Computer Security and Privacy, University of Goettingen, Goettingen, Germany
Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
Mar 23, 2026Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna +3Privacy Severity
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-GarciaSpeaker Anonymization
Centre for Language Studies · Institute for Computing and Information Sciences
Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
Mar 13, 2026Xiangkui Cao, Jie Zhang, Meina Kan +2Large Language Model Safety Recent Vision-Language Models
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences · University of Chinese Academy of Sciences
Bayesian Adversarial Privacy
Mar 4, 2026Cameron Bell, Timothy Johnston, Antoine Luciano +1Privacy Disclosures
CEREMADE, Université Paris Dauphine–PSL, France · Department of Statistics, University of Warwick, UK
Differential privacy representation geometry for medical image analysis
Mar 1, 2026Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung +1Δ)$-Differential Privacy Medical Images
Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany · INDA Institute, RWTH Aachen University, Aachen, Germany
PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems
Feb 21, 2026Nnaemeka Obiefuna, Samuel Oyeneye, Similoluwa Odunaiya +2Privacy-Utility Trade-Offs Privacy
1ML Collective · 2Friedrich-Alexander-Universität Erlangen-Nürnberg · 3Carnegie Mellon University
Efficient privacy loss accounting for subsampling and random allocation
Feb 19, 2026Vitaly Feldman, Moshe ShenfeldStandard Differential-Privacy Subsampling
Apple · The Hebrew University of Jerusalem · *Work partially done while author was an intern at Apple.
Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs
Feb 6, 2026Ying Song, Balaji PalanisamyMembership Inference Attacks Privacy
University of Pittsburgh Pittsburgh, PA, USA
On the Inherent Privacy Amplification of Missing Data
Feb 2, 2026Simon Roburin, Rafa{ë}l Pinot, Erwan ScornetMissing Data Privacy
LPSM · Sorbonne Université, Université Paris Cité, CNRS Laboratoire de Probabilités, Statistique et Modélisation (LPSM) F-75005 Paris, France
AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
Jan 30, 2026Jaehee Kim, Pilsung KangAttacker Large Language Model Privacy
Department of Industrial Engineering, Seoul National University, South Korea.
VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models
Jan 27, 2026Yuxiang Wang, Hongyu Liu, Dekun Chen +2Speech Language Models Speaker
The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute · Amphion Technology Co., Ltd. +1
NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents
Jan 21, 2026Saswat Das, Ferdinando FiorettoPrivacy Guardrail
University of Virginia
In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
Jan 19, 2026Anudeex Shetty, Aditya Joshi, Salil S. KanhereLarge Language Model Safety Jailbreak Attacks
School of Computer Science and Engineering, UNSW Sydney, Australia · School of Computing and Information System, the University of Melbourne, Australia
Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict
Jan 7, 2026Guanyu Chen, Chenxiao Yu, Xiyang HuLarge Language Model Alignment Human Values
Arizona State University · University of Southern California
User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios
Oct 23, 2025Xiaoyuan Wu, Roshni Kaushik, Wenkai Li +2Privacy Large Language Model Responses
Fujitsu Research of America, Inc. · Carnegie Mellon University
Overcoming Language Barriers: Multilingual Analysis of the 2023 Swiss Privacy Law's Impact
Oct 7, 2025Luka Nenadic, David Rodriguez, Joseph A. CalandrinoGerman Privacy
ETH Zurich Zurich, Switzerland · Information Processing and Telecommunications Center Universidad Politécnica de Madrid ETSI Telecomunicación, Spain · Carnegie Mellon University Pittsburgh, Pennsylvania, USA
Enforcing Speech Content Privacy in Environmental Sound Recordings using Segment-wise Waveform Reversal
Jul 11, 2025Modan Tailleur, Mathieu Lagrange, Pierre Aumond +1Speech Separation Speaker
Nantes Universit´e, ´Ecole Centrale Nantes, CNRS, LS2N, UMR 6004, Nantes, France · Universit´e Gustave Eiffel, CEREMA, UMRAE, Bouguenais, France · Nantes Universit´e, ENSA Nantes, ´Ecole Centrale Nantes, CNRS, AAU-CRENAU, Nantes, France
Efficient Unlearning with Privacy Guarantees
Jul 7, 2025Josep Domingo-Ferrer, Najeeb Jebreel, David SánchezMachine Unlearning Privacy-Preserving Machine Learning
1CYBERCAT (Center for Cybersecurity Research of2026 Catalonia), ComSCIAM-Center for Computational Science and Applied Mathematics, Department of Computer EngineeringJun and Mathematics, Universitat Rovira i Virgili, Av. Pa¨ısos26 Catalans 26, E-43007 Tarragona, Catalonia
Donate or Create? Comparing Data Collection Strategies for Emotion-labeled Multimodal Social Media Posts
May 30, 2025Christopher Bagdon, Aidan Combs, Carina Silberer +1Social Media Posts Emotion Recognition
Fundamentals of Natural Language Processing, University of Bamberg, Germany · Department of Sociology, The Ohio State University, USA · Institut für Maschinelle Sprachverarbeitung, University of Stuttgart, Germany
Privacy-Aware Visual Language Models
May 27, 2024Laurens Samson, Nimrod Barazani, Sennay Ghebreab +1Multimodal Benchmarks Privacy
Socially-Intelligent Artificial Systems Group, University of Amsterdam · University of Amsterdam · Fundamental AI Lab, University of Technology Nuremberg
BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines
Date pendingBo Ma, Jinsong Wu, Weiqi YanPrivacy Mediation
Auckland University of Technology Auckland, New Zealand · Guilin University of Electronic Technology Guilin, China
Label Differential Privacy via Aggregation
Date pendingAnand Brahmbhatt, Rishi Saket, Shreyas Havaldar +3Standard Differential-Privacy Δ)$-Differential Privacy
Google Research India.
Protect Your Score: Contact Tracing With Differential Privacy Guarantees
Date pendingRob Romijnders, Christos Louizos, Yuki M. Asano +1Δ)$-Differential Privacy Covid-19
University of Amsterdam · Qualcomm AI research
PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learning
Date pendingMojtaba Taherisadr, Salma ElmalakiCyber-Physical System Privacy
University of California, Irvine, USA
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Date pendingAnmol Goel, Iryna GurevychComputer-Use Agents Disclosures
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE
DNA: Differentially private Neural Augmentation for contact tracing
Date pendingRob Romijnders, Christos Louizos, Yuki M. Asano +1Covid-19 Δ)$-Differential Privacy
University of Amsterdam · Qualcomm AI research

Apr 20, 2026, cs.CRJ/K move · Enter open · S save

Tight Auditing of Differential Privacy in MST and AIM

Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Bogdan Kulynych

1UCL · 2SAS · 3Lausanne University Hospital

Standard Differential-Privacy Privacy Fairness Audits Model Auditing Distributional Fidelity Synthetic Data

Open paper AskPDF arXiv

State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy (GDP)-based auditing framework that measures privacy via the full false-positive/false-negative tradeoff. Applied to MST and AIM under worst-case settings, our method provides the first tight audits in the strong-privacy regime. For

(ε,δ)=(1,10^{-2})

, we obtain

μ_{emp}\approx0.43

vs. implied

μ=0.45

, showing a small theory-practice gap. Our code is publicly available: https://github.com/sassoftware/dpmm.

Momentum

Related topics

Latest papers 275