Privacy-Preserving Technologies in Data

Latest papers

• FedMIX-P: Mixing Local and Global Preconditioners for Federated Vision and Language Model Training

  Junkang Liu · 2 October 2026

  Adaptive preconditioners accelerate model training, but heterogeneous client geometries can bias federated updates even when gradients are evaluated at the same model. Round-start synchronization alone cannot prevent this mismatch from reappearing during local training. We propose \texttt{FedMIX-P},…

• FedLore: Communication and Memory Efficient Federated Learning via Shared Gradient Low-Rank Projection

  Junkang Liu · 2 October 2026

  Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank adapters, but their fixed rank budget can limit adaptation. Gradient low-rank optimization offers greater flexibility, yet independently chosen clie…

• Federated Agent Optimization

  Qiang Yang, Zhiqiang Kou, Xueyi Zhang, Dong-Dong Wu, Hanlin Gu, Jing Guo, Yang Liu, Di Jiang, Qian Xu · 2 October 2026

  Large language model (LLM) agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedback, and local knowledge. Yet such experience is distributed across organizations and cannot be directly shared because of privacy and proprietary con…

• Unapologetically Distributed: A Call for Decentralized Document Analysis

  Adri\`a Molina, Oriol Ramos Terrades, Josep Llad\'os · 1 October 2026

  Privacy has become an increasingly important concern in the Document Analysis community, to the extent that in many environments such as archives, governmental institutions, and local businesses, the adoption of automation is restricted by legal and policy constraints. While federated learning has o…

• HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge Devices

  Qiyuan Chen, Xian Wu, Yanan Ma, Xianhao Chen · 1 October 2026

  Federated learning (FL) on memory-constrained edge devices faces a dilemma: first-order (FO) optimization (i.e., backpropagation) demands substantial memory, whereas zeroth-order (ZO) optimization suffers from severe convergence slowdown. To resolve this dilemma, we introduce HO-FL, a hybrid-order F…

• Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning

  Chaoyu Zhang, Shanghao Shi, Heng Jin, Ning Wang, Y. Thomas Hou, Wenjing Lou · 1 October 2026

  Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly train diagnostic models without exchanging patient records. This privacy promise, however, is increasingly contested: a malicious or honest-but-curious se…

• Prototype-guided Bilateral Alignment Multimodal Federated Learning

  Tianchi Liao Tianchi_Liao, Lele Fu, Sheng Huang, Qing Hu, Hong-Ning Dai, Chuan Chen · 1 October 2026

  Multimodal federated learning (MFL) has emerged as a pivotal paradigm for leveraging distributed data to enhance model performance. However, existing methods predominantly rely on idealized assumptions of model homogeneity and balanced modality distributions, rendering them ill-suited for practical …

• FedSocket: Recipient-Executable Knowledge Exchange for Heterogeneous Multimodal Federated Learning

  Xinyuan Zhao · 30 September 2026

  Federated knowledge must remain usable by recipients with different modalities, private architectures, and tasks. We present FedSocket, which makes recipient execution a design requirement of the exchanged model. A shared Q combines recipient-computable inputs, task-owned outputs, and ownership-awar…

• OPFL: Optimistic Verification of Federated Learning via Empirical Boundary

  Hongxu Su, Jianzhu Yao, Xuechao Wang, Pramod Viswanath · 30 September 2026

  Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into local training makes it difficult to verify whether clients follow the prescribed training procedure or submit malicious updates, such as model poisoni…

• Calibrating One-Round Membership Inference with Neighbors

  Francesco Rita, Jie Zhang, Florian Tram\`er · 30 September 2026

  The state-of-the-art Membership Inference (MI) methods calibrate their signal separately for each example using reference models, auxiliary models trained to exclude the target. This paradigm scales poorly to modern large models, however, whose training is too expensive to replicate. This has motiva…

• DecoyTrace: Toxic Decoys for Active Defense in Decentralized Federated Learning

  Pedro Beltr\'an-L\'opez, Enrique Tom\'as Mart\'inez Beltr\'an, Pantaleone Nespoli, Manuel Gil P\'erez, Alberto Huertas Celdr\'an · 30 September 2026

  Decentralized Federated Learning (DFL) eliminates the central aggregation server, reducing the single point of observation that traditional defenses against attacks rely on. As a result, peer-to-peer networks become exposed to malicious updates containing backdoors or semantic poisoning, since such …

• Encoder-Sharing Hierarchical Federated Multi-Task Learning for VANETs

  M. Saeid HaghighiFard, Sinem Coleri · 30 September 2026

  Most federated learning frameworks for vehicular ad hoc networks assume that all vehicles collaboratively train a single model for a common task. This assumption limits their applicability to practical vehicular environments, where vehicles may perform heterogeneous but related perception tasks with…

• FedLAFP: Low-Rank Aggregation Meets Full-Rank Personalization in Federated Fine-Tuning

  Mengjun Yi, Huaian Gu, Yinghao Ai, Furao Shen, Jian Zhao · 30 September 2026

  Federated parameter-efficient fine-tuning enables clients to adapt pre-trained models without sharing raw data or communicating the full model, but statistical heterogeneity makes a single global adapter insufficient for personalized prediction. Existing personalized methods typically use the same l…

• CF-LoRA: Decoupled Factor Aggregation and Adaptation-Aware Client Clustering for Federated LoRA Fine-Tuning

  Mengjun Yi, Langxing Yang, Suhan Guo, Furao Shen, Jian Zhao · 30 September 2026

  Federated LoRA fine-tuning enables parameter-efficient adaptation of pre-trained models without sharing private data, but suffers from two fundamental mismatches under heterogeneous client data: a structural aggregation mismatch caused by independently averaging LoRA factors, and a statistical colla…

• Collaborative Synthetic Data for Privacy-Preserving Financial Fraud Detection Across Organizational Silos

  Simeon Allmendinger, Domenique Zipperling, Burhanettin Bahadir Kibar, Niklas K{\"u}hl · 29 September 2026

  Organizations seek analytical value from AI, yet relevant data are often fragmented across organizations and constrained by privacy. This is acute in financial fraud detection, where rare fraud cases and imbalanced local datasets limit decision-relevant analytics. Federated learning enables collabor…

• CoeF-SFL: Preserving Collaborative Server-Client Learning with Enhanced Communication Efficiency

  Junwoo Bae, Jin-Hyun Ahn · 29 September 2026

  Split Federated Learning (SFL) enables resource-constrained clients to participate in collaborative training, but vanilla SFL exchanges smashed data and gradients at every batch, which incurs significant communication overhead. Recent methods reduce this overhead with an auxiliary network at the cli…

• Differentially-Private Decision Trees and Provable Robustness to Data Poisoning

  Dani\"el Vos, Jelle Vos, Tianyu Li, Zekeriya Erkin, Sicco Verwer · 28 September 2026

  Decision trees are interpretable models that are well-suited to non-linear learning problems. Much work has been done on extending decision tree learning algorithms with differential privacy, a system that guarantees the privacy of samples within the training data. However, current state-of-the-art …

• Gap-free Differentially Private PCA for Gaussian Data

  Alina Ene, Huy L. Nguyen · 28 September 2026

  We give a gap-free differentially private algorithm for the principal component analysis (PCA) problem with Gaussian data.…

• Distributed Learning as a Service: The Developer's Perspective

  Tianyue Chu, Filippo Vannella, Dimitra Tsigkari, Paula Delgado-Santos, Fernando L\'opez, Pablo Gomez Guerrero, Sotirios Spantideas, David Solans Noguero · 28 September 2026

  Application developers of distributed learning services face challenges that a typical federated learning loop does not address. Specifically, the model updates can still leak private data, devices might not be able to participate in the training due to limited resources, a single aggregator might n…

• Federated Targeted Maximum Likelihood Estimation

  Diyang Li, Fei Wang, Kyra Gan · 28 September 2026

  The evidence behind a scientific or operational decision is often held by hospitals, banks, or registries that cannot pool individual observations. Cross-silo federated learning moves computation to the data and exchanges agreed summaries. Targeted maximum likelihood estimation (TMLE) refines a flex…

• Uncertainty-Aware Federated Learning for Infant Movement Analysis

  Edmond S. L. Ho · 28 September 2026

  Infant movement analysis provides valuable biomarkers for the early identification of neurodevelopmental disorders. Recent advances in deep learning have enabled automated analysis of infant movements from video-derived skeletal representations, achieving performance comparable to expert assessment …

• Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality

  Bradley Scott, Zeqi Luo, Edmond S. L. Ho · 28 September 2026

  Federated learning (FL) data corruption can affect either inputs or labels, but it remains unclear whether input-conditional uncertainty and prediction-label loss expose these corruption modes equally. This paper compares two corruption-detection signals in FL: input-conditional uncertainty and pred…

• Concurrent Split Learning Through Stable Client Clustering

  Mohammad Kohankhaki, Valentin Rentschler, Anke Schmeink · 25 September 2026

  Training with a fixed global batch limits how many distributed clients can provide examples in any one step. We examine a way to use additional server workers without increasing the batch processed by an individual workload. Global Clustered Parallel Split Learning (GCPSL) assigns clients to fixed c…

• BRFID: Toward Byzantine-Robust Federated Intrusion Detection

  Asmah Muallem, Firdous Kausar, Sajid Hussain, Lei Qian · 25 September 2026

  Flipping 60\% of training labels from a single Byzantine client using label-flipping model poisoning self-degrades an attacker's own federated detection accuracy, $99.96\%$ (at no poisoning rate) to $84.33\%$ in a three-client federated IDS. Where the Federated global ensemble maintains stable accur…

• Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities

  Pravija Raj P V, Ashish Gupta, Andrea Augello, Sajal K. Das · 25 September 2026

  While Federated Learning (FL) has been widely adopted for protecting user privacy in machine learning, it remains vulnerable to various robustness challenges, including performance-impairment risks, information-stealing threats, and aggregation vulnerabilities. This work offers a holistic synthesis …