Latest Privacy-Preserving ML Research Papers

The newest Privacy-Preserving ML papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Privacy-Preserving ML so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Beyond GDPR: The Architectural Challenge of Data Sovereignty and Confidential Computing in the Post-2024 Era
  Mr. Tayabur Rahman Laskar · International Comprehensive... · Dec 18, 2026

  As organizations migrate legacy datasets to cloud-native architectures, the tension between Big Data analytics and data privacy regulations has reached a critical inflection point. With the full operationalization of India’s Digital Persona…

• FedSTD: Federated Learning with Spatio-Temporal Decoupling for Cross-Modal Transport Prediction
  Fabrice Marggi, Eric Samikwa, Torsten Ingo Braun · Open Access CRIS of the Uni... · Dec 15, 2026

  Modern transportation systems are shaped by multiple interdependent modes of transport. Understanding their interactions is essential for effective management and planning. Cross-modal flow and demand predictions can improve forecasting acc…

• The Privacy and Security Risks of Edge LLM Optimization
  Mingchen Li, Ren-Yi Huang, Dumindu Samaraweera, Prashant Shekhar et al. · arXiv · Oct 29, 2026

  Edge deployment of Large Language Models requires optimization techniques that reduce memory, computation, and energy costs. However, preserving task performance does not necessarily preserve security. We argue that optimization is an infor…

• Investigating Data Flows from Android Games
  Judit Borcsiczky, Lukas Moog, Boel Nelson · arXiv · Oct 29, 2026

  Online applications can share data with arbitrary parties, without users noticing. In practice, these data flows could constitute privacy violations to individual users, with the lack of transparency leaving users unaware of the unwanted da…

• Hardware-Aware Model Inversion in Memristive Spiking Neural Networks
  Pablo Sorrentino, Fernando M. Quintana, Erika Covi, Fatih Turkmen · arXiv · Oct 29, 2026

  Hardware-accelerated spiking neural networks (SNNs) implemented on memristive crossbar arrays offer significant gains in energy efficiency, while device variability and analog noise are sometimes assumed to hinder information extraction. Ho…

• Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy
  Hengyu Wu, Blaise Delattre, Yang Cao · arXiv · Oct 29, 2026

  Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual interactions: a release appropriate in isolation may become inappropriate wh…

• Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
  Muhammad Uzair Shahid, Muhammad Zabil Mehboob · arXiv · Oct 29, 2026

  Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requires training on sensitive data from multiple organizations, putting privacy and the transparency demanded by forensic r…

• DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3
  Hong Lin, Zhongle Xie, Lidan Shou, Ke Chen et al. · arXiv · Oct 29, 2026

  Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly. Blockchain-powered federated learning (BCFL) offers a secure and privacy-preserving paradigm to cust…

• Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness
  Long Dang, Ali Alfatemi, Kaiqi Xiong, Mohammed Aledhari et al. · arXiv · Oct 28, 2026

  Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development across cloud-edge-IoT systems without fully centralizing raw data. However, distributing da…

• Complexity of Differentially Private Selection via Federated APIs
  Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen et al. · arXiv · Oct 28, 2026

  Differential privacy (DP) has become the standard for privacy-preserving data analysis, yet its practical implementation in federated or distributed settings often faces a significant utility gap compared to the central model. While existin…

• STAR: Scalable TEE-based Anonymous Rate-limiter
  Kosei Akama, Yoshimichi Nakatsuka, Koichi Moriyama, Keisuke Uehara · arXiv · Oct 28, 2026

  Protecting Internet services from attacks such as TLS/HTTP floods requires rate limiting, yet identifying users to enforce these limits can compromise their privacy. Anonymous rate limiting promises to reconcile these goals, but existing sc…

• The State of the Practice in Privacy Impact Assessments: Understanding the Professionals' Perspectives, Experiences, and Current Procedures
  Samuel Wairimu, Leonardo Horn Iwaya, Ala Sarah Alaqra · arXiv · Oct 28, 2026

  Organisations frequently utilise Privacy Impact Assessments (PIAs), Data Protection Impact Assessments (DPIAs), or even Fundamental Rights Impact Assessments (FRIAs) to identify and evaluate potential risks and possible infringements of fun…

• Rosemary: Efficient and Adaptable In-Storage Acceleration for Fully Homomorphic Encryption
  Xuan Wang, Tianqi Zhang, Gabrielle De Micheli, Yujin Nam et al. · arXiv · Oct 28, 2026

  Fully Homomorphic Encryption (FHE) enables computation on encrypted data and is promising for privacy-preserving computing. However, FHE deployment remains constrained due to massive computational, memory, and data-movement overheads. Exist…

• SPARSEBLEED: Bypassing Attribute-Inference Defenses via Sparsity Optimizations
  Darsh Asher, Farshad Dizani, Joshua Kalyanapu, Ro Cammarota et al. · arXiv · Oct 28, 2026

  Deep neural networks (DNNs) are widely deployed in safety- and privacy-critical domains such as healthcare and finance, where models are trained on confidential data. This paper presents the first hardware-level attribute-stealing attack th…

• Revisiting Privacy Risks in Quantized Deep Neural Networks
  Jie Fu, Ren Li, Wendy Hui Wang · arXiv · Oct 27, 2026

  Model quantization has become a fundamental technique for enabling the efficient deployment of large-scale deep neural networks (DNNs) in data-intensive applications by reducing model size. Despite its widespread adoption, the impact of qua…

• Penny for Your Prompts: A Measurement Study of Contextual Leakage in AI Chat Platforms
  Paschalis Bekos, Billy Tsouvalas, Nick Nikiforakis, Michalis Polychronakis · arXiv · Oct 27, 2026

  AI chatbot platforms have become one of the most popular web interfaces users interact with online, routinely receiving personal and intimate information shared under an expectation of privacy. Yet, on the web application side, these platfo…

• The Content Leash: Mitigating Degenerate Solutions in Invertible Speaker Anonymization
  Nirjon Mobarak Talukder, Rafid Ahmed, Mohammad Ishrak Abedin, Abu Raihan Mostofa Kamal · arXiv · Oct 27, 2026

  Voice anonymization aims to protect a speaker's identity while preserving the linguistic content of speech, enabling voice data to be shared and processed with reduced privacy risk. This work focuses on reversible voice anonymization, where…

• PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses
  Krishna Kanth Nakka, Yujun Wang, Shijie Zhou, Tu Nguyen et al. · arXiv · Oct 27, 2026

  Reliable evaluation is a critical bottleneck in privacy red-teaming of large language models (LLMs): determining whether a jailbreak response actually reveals personal information can be difficult when disclosures are indirect, contextual, …

• Measuring Users' Security and Privacy Concerns About Third-Party Community Bots on Discord
  Kofi Ampomah, Tu Le · arXiv · Oct 27, 2026

  Third-party community-based bots are central to how social platforms such as Discord work. They moderate content, manage roles, play music, and support AI-assisted conversations across millions of servers. Yet when a bot is installed in a s…

• Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging
  Malithi Mithsara Wanniarachchi Kankanamge, Ning Yang, Sree Bash Debnath, Md Zobaer Islam et al. · arXiv · Oct 26, 2026

  Artificial intelligence (AI) shows promise for breast imaging, but limited labeled data, institutional data fragmentation, and privacy concerns hinder centralized training. We investigate a privacy-aware federated learning framework combini…

• Privately Clipping Heavy-Tailed Data
  Matthew Joseph, Alex Kulesza · arXiv · Oct 26, 2026

  Summing vectors is a basic task in differentially private data analysis. Standard private sum algorithms clip vectors to some bound, sum them, and add noise scaled to the bound. The differential privacy literature has developed a deep libra…

• A Category-Selective Encryption Framework for Privacy Protection of UAV Images
  Ting Yan, Minghui Shang, Haolang Sun, Xu Wang et al. · arXiv · Oct 26, 2026

  Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillance routinely captures sensitive objects such as pedestrians and vehicles alongside ordinary scene content. Existing priv…

• PRISMA: Differentially Private Synthetic In-Car Telemetry via Differentiable Simulation
  Kilian Zeiseweis, Nele Sophie Brügge, Marven Kummerfeldt, Ali Raza et al. · arXiv · Oct 26, 2026

  Differentially private synthesis of in-car energy consumption data is challenging because the output is high-dimensional, and known lower bounds show that the privacy-utility trade-off degrades with the square root of the number of output d…

• Pricing Cross-Bank Context in Federated Anti-Money Laundering
  Lidia Losavio, Dario Fenoglio, Martin Gjoreski, Marc Langheinrich · arXiv · Oct 26, 2026

  Most graph-based Anti-Money Laundering (AML) methods assume access to a pooled transaction graph containing all accounts and payments, which in reality does not exist. Federated learning offers the necessary privacy guarantees but it remain…

• HNSecW: A Logarithmic-Time MPC Protocol for Approximate Nearest Neighbor Search
  Fahong Zhang, Weijie Jin, Lixu Wang, Ning Luo et al. · arXiv · Oct 25, 2026

  As a core component of modern RAG systems, approximate nearest neighbor (ANN) search has been extensively studied for decades. In practice, deploying ANN often requires symmetric privacy, where the querier's query and the database owner's d…

• Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service
  Yang Li, Gang He, Ruichen Zhang, Guangyuan Liu et al. · arXiv · Oct 24, 2026

  Machine Learning as a Service (MLaaS) has become a popular paradigm for deploying AI applications. However, it raises significant privacy concerns that the raw client data needs to be uploaded to the server for inference services. Private i…

• Holo-NN: Holographic Nearest Neighbor Search via Compressive Sensing
  Bryant Gipson · arXiv · Oct 23, 2026

  In the age of AI, privacy-preserving approximate nearest neighbor (ANN) search over high-dimensional embeddings has emerged as a critical yet frustratingly challenging domain, dominated by tradeoffs between speed, privacy, and accuracy. Tra…

• A-GE: Privacy-Preserving Age Assurance via Fine-Grained Motion
  Mohammed Gharib, Giovanni Cascone, Martin Zizi · arXiv · Oct 23, 2026

  Age assurance faces a fundamental privacy dilemma: meaningful assurance typically requires revealing identity or other sensitive information, whereas privacy-preserving alternatives often provide little assurance. Existing approaches either…

• Privacy-Preserving Federated Loss Exploration for Vision-Based Perception under Non-IID Data
  Nergiz Yuca, Christian Internò, Nikolay Matyunin, Markus Olhofer et al. · arXiv · Oct 23, 2026

  Vision-based image classification models benefit from Federated Learning (FL) across vehicles, however learning accurate models from distributed vehicular cameras is challenging due to data heterogeneity and privacy concerns. To improve per…

• Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information
  Xincheng Xu, Thilina Ranbaduge, Thierry Rakotoarivelo, David Smith · arXiv · Oct 23, 2026

  Differentially Private Stochastic Gradient Descent (DPSGD) has become the de facto standard for training deep neural networks with rigorous privacy guarantees. However, the utility of DPSGD is constrained by gradient clipping bias and DP no…