Pith. sign in

REVIEW 49 cited by

Differentially Private Federated Learning: A Client Level Perspective

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1712.07557 v2 pith:UV7FY4GU submitted 2017-12-20 cs.CR cs.LGstat.ML

Robin C. Geyer , Tassilo Klein , Moin Nabi This is my paper · ORCID
classification cs.CRcs.LGstat.ML
keywords modelclientsfederatedprivacyclientdifferentialduringdata
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to share the data. However, the protocol is vulnerable to differential attacks, which could originate from any party contributing during federated optimization. In such an attack, a client's contribution during training and information about their data set is revealed through analyzing the distributed model. We tackle this problem and propose an algorithm for client sided differential privacy preserving federated optimization. The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance. Empirical studies suggest that given a sufficiently large number of participating clients, our proposed procedure can maintain client-level differential privacy at only a minor cost in model performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 49 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes

    stat.ML 2026-08 conditional novelty 7.0 of 10

    VANEB generalizes nonparametric empirical Bayes to parameter-dependent noise and uses it to personalize federated models by shrinking local estimates toward a learned population prior.

  2. TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

    cs.CR 2026-06 unverdicted novelty 7.0 of 10

    TIGER turns the low-rank attention gradient subspace into a differentiable objective for continuous embedding optimization, improving reconstruction quality and robustness over prior discrete token tests especially un...

  3. DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models

    cs.LG 2026-02 unverdicted novelty 7.0 of 10

    DP-FedAdamW delivers an unbiased second-moment estimator for AdamW in DPFL, proving linear convergence acceleration without heterogeneity assumptions and outperforming SOTA by 5.83% on Tiny-ImageNet with Swin-Base at ε=1.

  4. Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings

    cs.LG 2025-06 conditional novelty 7.0 of 10

    FedLeak reconstructs high-fidelity images from federated learning gradients at practical batch sizes, without auxiliary data, by matching only the largest gradient components and regularizing the optimization.

  5. Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning

    cs.CV 2024-11 unverdicted novelty 7.0 of 10

    DMBA maintains attack success rates above 80% for all backdoors in a distributed multi-target FL setting where baselines drop below 50%.

  6. Convergent Differential Privacy Analysis for General Federated Learning

    cs.LG 2024-08 unverdicted novelty 7.0 of 10

    Proves convergent privacy bounds for Noisy-FedAvg and stable lower bounds for Noisy-FedProx in FL-DP via f-DP and shifted interpolation, replacing divergent composition bounds.

  7. Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning

    cs.CR 2026-08 conditional novelty 6.0 of 10

    Fairis shows that weighting a client by a security parameter minus its local fairness score makes its aggregation weight strictly decrease with reported bias, while keeping every client's weight positive.

  8. Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Clients encode private images through a frozen public autoencoder, compute additive class-conditional latent statistics protected by differential privacy, and the server decodes a synthetic dataset that trains competi...

  9. Robust Federated Learning Under Real-World Client Churn

    cs.LG 2026-07 conditional novelty 6.0 of 10

    FeLiX reduces wall-clock time-to-target accuracy in federated learning by up to 2.37x using lightweight availability tiers, fresh-utility client selection, and informativeness-aware aggregation without requiring oracu...

  10. CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    CausShield decomposes VFL representations via causal representation learning to resist sample reconstruction attacks while preserving utility and convergence.

  11. DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning

    cs.CR 2026-06 unverdicted novelty 6.0 of 10

    DIST-FL distributes TEE-guarded servers into an append-only ledger to ensure linearizable FL aggregation and counter rollback plus I/O attacks while matching single-TEE speed.

  12. Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning

    stat.ML 2026-05 unverdicted novelty 6.0 of 10

    Introduces FedHybrid and FedNewton for DP federated M-estimation, with finite-sample MSE bounds, minimax lower bound, and evaluations on vision datasets.

  13. Practical Quantum Federated Learning for Privacy-Sensitive Healthcare: Communication Efficiency and Noise Resilience

    quant-ph 2026-03 unverdicted novelty 6.0 of 10

    Hybrid QFL cuts quantum transmissions from 3TNMP to {3t + 2(T-t)}NMP over T rounds while preserving near-centralized convergence and improving depolarizing-noise resilience via decentralized aggregation and Steane-code QEC.

  14. Sketched Gaussian Mechanism for Private Federated Learning

    cs.LG 2025-09 conditional novelty 6.0 of 10

    A sketched Gaussian mechanism is shown to have privacy loss that shrinks as the sketch dimension grows, giving communication-efficient federated learning with stronger privacy per noise budget.

  15. Cyst-X: A Multi-Center MRI Benchmark and Federated Learning Framework for Malignancy-Risk Stratification of Pancreatic Cystic Neoplasm

    eess.IV 2025-07 conditional novelty 6.0 of 10

    A multi-center MRI benchmark and federated learning framework for IPMN malignancy-risk stratification, with an internal AUC of 0.85 on T2-weighted MRI.

  16. Asymptotically Optimal Secure Aggregation for Wireless Federated Learning with Multiple Servers

    cs.IT 2025-06 reject novelty 6.0 of 10

    A multi-server wireless federated learning scheme combining secret sharing and artificial noise alignment achieves communication latency within a factor of 4 of the information-theoretic optimum, and is asymptotically...

  17. CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling

    cs.LG 2025-01 reject novelty 6.0 of 10

    CENSOR defends federated learning against gradient inversion by transmitting a loss-optimized random gradient orthogonal to the true gradient, but its security claim is not established against adaptive adversaries.

  18. TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning

    cs.CR 2025-01 reject novelty 6.0 of 10

    TAPFed introduces a threshold functional encryption scheme that lets federated learning aggregate encrypted model updates across multiple independent aggregators while tolerating up to t-1 malicious ones.

  19. A New Federated Learning Framework Against Gradient Inversion Attacks

    cs.LG 2024-12 conditional novelty 6.0 of 10

    HyperFL defends against gradient inversion by sharing only hypernetwork-generated weights, achieving DP-level privacy with higher accuracy.

  20. FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection

    cs.LG 2025-09 reject novelty 5.0 of 10

    FedRP claims to preserve FedAvg-level accuracy while sending only a few numbers per client per round and providing an (epsilon, delta)-DP guarantee.

  21. Enhancing Model Privacy in Federated Learning with Random Masking and Quantization

    cs.LG 2025-08 reject novelty 5.0 of 10

    FedQSN hides part of the server model with random masks and quantizes the remainder to give clients a degraded proxy, reporting a large global-vs-proxy performance gap with modest loss in the final global model.

  22. FLsim: A Modular and Library-Agnostic Simulation Framework for Federated Learning

    cs.DC 2025-07 conditional novelty 5.0 of 10

    FLsim is a modular, library-agnostic federated learning simulation framework supporting custom strategies, multiple topologies, and pluggable blockchain consensus.

  23. Convergence of Agnostic Federated Averaging

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Agnostic FedAvg converges at O(1/sqrt T) to the availability-weighted objective under unknown non-uniform client participation, for convex losses.

  24. Learning Private Representations through Entropy-based Adversarial Training

    cs.LG 2025-07 reject novelty 5.0 of 10

    Focal entropy, an off-centered entropy that focuses confusion on similar sensitive classes, improves the utility versus privacy trade-off in adversarial representation learning.

  25. One-Bit Model Aggregation for Differentially Private and Byzantine-Robust Personalized Federated Learning

    cs.DC 2025-07 reject novelty 5.0 of 10

    PRoBit+ combines one-bit stochastic quantization, ML-based aggregation, and an adaptive quantization range to achieve communication-efficient, differentially private, Byzantine-robust personalized federated learning.

  26. Shadow defense against gradient inversion attack in federated learning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A shadow-model-based defense adds sample-specific noise to medical images in federated learning, weakening gradient inversion attacks while keeping model accuracy near baseline.

  27. Multi-Modal One-Shot Federated Ensemble Learning for Medical Data with Vision Large Language Model

    cs.LG 2025-01 conditional novelty 5.0 of 10

    FedMME fuses vision-LLM-generated text features with image features and uses client voting to improve one-shot federated medical image classification.

  28. Hidden Data Privacy Breaches in Federated Learning

    cs.CL 2024-11 conditional novelty 5.0 of 10

    A malicious federated learning server can hide a secret model inside client parameters via code injection and later reconstruct the client's training images from Fibonacci-coded index queries.

  29. An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning

    cs.LG 2019-08 reject novelty 5.0 of 10

    An autoencoder-based gradient compression scheme for federated learning that decodes the aggregated update directly, with claims of privacy and reduced communication that are only weakly supported.

  30. Threat Vectors and the State of the Art in Defense Methods for Security in Neurotechnology

    cs.CR 2026-07 conditional novelty 4.5 of 10

    Neurosecurity lags BCI capability; a full-stack attack-surface taxonomy plus transferable defenses from cyber, hardware security, and private ML can close many gaps immediately.

  31. Compliance Management for Federated Data Processing

    cs.SE 2026-02 unverdicted novelty 4.0 of 10

    A prototype framework collects legal requirements and translates them into machine-actionable policies for federated data processing networks via policy-as-code and LLMs.

  32. PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems

    cs.CR 2026-02 conditional novelty 4.0 of 10

    Combining federated learning with differential privacy causes catastrophic accuracy loss and large resource overhead in vision models, whereas federated learning with secure multi-party computation retains near-baseli...

  33. Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise

    stat.ML 2025-09 reject novelty 4.0 of 10

    The paper proposes CAPE-assisted federated DP-CDA for private synthetic data generation, but the privacy analysis is flawed.

  34. A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives

    cs.CR 2025-08 conditional novelty 4.0 of 10

    The paper classifies model extraction attacks and defenses into attack, defense, and computing environment categories and surveys their current state.

  35. FedGA: A Fair Federated Learning Framework Based on the Gini Coefficient

    cs.LG 2025-07 conditional novelty 4.0 of 10

    FedGA, a fairness-aware federated learning method, uses the Gini coefficient to trigger delayed reweighting of aggregation toward low-accuracy clients, improving fairness metrics while maintaining accuracy on three datasets.

  36. Decoding Federated Learning: The FedNAM+ Conformal Revolution

    cs.LG 2025-06 reject novelty 4.0 of 10

    FedNAM+ couples Neural Additive Models with a gradient-based Dynamic Level Adjustment scheme for uncertainty in federated learning, but the coverage guarantee is not established.

  37. LAPA-based Dynamic Privacy Optimization for Wireless Federated Learning in Heterogeneous Environments

    cs.LG 2025-05 reject novelty 4.0 of 10

    A new adaptive privacy allocation and transmission power control scheme for wireless FL is proposed, with a convergence bound and MNIST/Fashion-MNIST experiments, but the DP sensitivity calibration and noise-switch co...

  38. Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare

    cs.LG 2025-05 reject novelty 4.0 of 10

    A reputation-aware federated survival analysis framework using DP-protected peer feedback and clustering reports stable C-index gains, but its convergence argument assumes the true reliability it claims to prove.

  39. Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Federated averaging of behavior-metric-based state projection networks improves cross-environment generalization in federated reinforcement learning, while the claimed privacy protection is not demonstrated.

  40. Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security

    cs.CR 2025-05 conditional novelty 4.0 of 10

    Beskar combines one-round post-quantum secure aggregation with precomputed signatures and masks, plus differential privacy at multiple stages, to protect gradients, intermediate models, and deployed models in federate...

  41. Private Federated Learning In Real World Application -- A Case Study

    cs.LG 2025-02 conditional novelty 4.0 of 10

    A case study showing that private federated learning can fine-tune an app selection model on-device, achieving a small accuracy gain over a static server-trained baseline.

  42. Metric Privacy in Federated Learning for Medical Imaging: Improving Convergence and Preventing Client Inference Attacks

    cs.LG 2025-02 reject novelty 4.0 of 10

    Server-side metric privacy, with noise scaled by a distance between client model updates, improves federated learning accuracy over global differential privacy in their experiments, but the claimed privacy protection ...

  43. Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL

    cs.LG 2024-12 reject novelty 4.0 of 10

    In a simplified net-zero microgrid, untuned federated TRPO learns useful battery policies, but tuned PPO gets much closer to the known optimal policy; personal encoding and feature grouping sometimes shrink the gap.

  44. Membership Inference Attacks and Defenses in Federated Learning: A Survey

    cs.CR 2024-12 conditional novelty 4.0 of 10

    A comprehensive survey of membership inference attacks and defenses in federated learning, proposing update-based and trend-based attack taxonomies and four defense categories.

  45. Upcycling Noise for Federated Unlearning

    cs.LG 2024-12 reject novelty 4.0 of 10

    FUI claims to erase a client's data in differentially private federated learning by retracting the local model and adding calibrated Gaussian noise to mimic retraining.

  46. DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences

    cs.LG 2025-07 reject novelty 3.0 of 10

    DRAGD and DRAGDP reconstruct erased federated-learning images by sequentially matching post-unlearning and pre-unlearning gradients, with DRAGDP adding a public-image prior.

  47. RiM: Record, Improve and Maintain Physical Well-being using Federated Learning

    cs.LG 2025-05 reject novelty 3.0 of 10

    A federated-learning mobile app predicts sleep and distance deficits from the same features used to define those deficits, so its reported 60.71% accuracy does not demonstrate predictive efficacy.

  48. Towards One-shot Federated Learning: Advances, Challenges, and Future Directions

    cs.LG 2025-05 conditional novelty 1.0 of 10

    A literature survey of one-shot federated learning that organizes methods, datasets, and code, but reports no new experimental or theoretical results.

  49. Federated Learning: Challenges, Methods, and Future Directions

    cs.LG 2019-08 unverdicted

    This survey maps federated learning's core challenges, reviews existing methods, and lists open problems.

Pith tools