Browse State-of-the-Art › Privacy Preserving Deep Learning
Privacy Preserving Deep Learning
30 papers with code · 0 benchmarks · 3 datasets archive 2025-07-28
The goal of privacy-preserving (deep) learning is to train a model while preserving privacy of the training dataset. Typically, it is understood that the trained model should be privacy-preserving (e.g., due to the training algorithm being differentially private).
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
2 subtasks in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 59 · with a code link: 30 · where Syntology ran a sample: 6 (3 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 59 tagged: 3 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 59 of 59, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
12 Jun 2019 5 repositories listedWe first discuss an innovative heuristic of cross-dataset training and evaluation, enabling the use of multiple single-task datasets (one with target task labels and the other with privacy labels) in our problem.
-
1 Jun 2020 3 repositories listedWe study locally differentially private (LDP) bandits learning in this paper.
-
9 Nov 2018 3 repositories listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)We detail a new framework for privacy preserving deep learning and discuss its assets.
-
3 Feb 2023 2 repositories listedIn this work, we evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training.
-
26 Jul 2021 2 repositories listedIn this work, we ask: Is it feasible to substitute all ReLUs with low-degree polynomial activation functions for building deep, privacy-friendly neural networks?
-
8 Jun 2020 2 repositories listedWe evaluate our end-to-end system for private inference between distant servers on standard neural networks such as AlexNet, VGG16 or ResNet18, and for private training on smaller networks like LeNet.
-
16 May 2025 1 repository listedBy replacing standard non-linearities with polynomial activations, Polynomial Neural Networks (PNNs) are pivotal for applications such as privacy-preserving inference via Homomorphic Encryption (HE).
-
16 Dec 2024 1 repository listedVertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection.
-
27 Aug 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)DCT-CryptoNets also demonstrates superior scalability to RGB-based networks by further reducing computational cost as image size increases.
-
17 Jul 2024 1 repository listedThis work addresses these challenges exploring and quantifying the utility of privacy-preserving deep learning techniques, concretely, (i) differentially private stochastic gradient descent (DP-SGD) and (ii) fully…
-
8 Apr 2024 1 repository listedTo address these challenges, we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning.
-
1 Oct 2023 1 repository listedSo far, the impact of training strategy, i. e., local versus collaborative, on the diagnostic on-domain and off-domain performance of AI models interpreting chest radiographs has not been assessed.
-
30 Aug 2023 1 repository listedThe idea behind it is that the client encrypts the activation map (the output of the split layer between the client and the server) before sending it to the server.
-
7 Dec 2022 1 repository listedOne such risk is training data extraction from language models that have been trained on datasets, which contain personal and privacy sensitive information.
-
24 Nov 2022 1 repository listedDue to the rapid advancements in recent years, medical image analysis is largely dominated by deep learning (DL).
-
21 Nov 2022 1 repository listedThe introduced DP should help limit leakage threats posed by MIAs, and our practical analysis is the first to test this hypothesis on the COVID-19 classification task.
-
11 Jul 2022 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)In this work, we propose a general family of optimization problems, termed as complexity-leakage-utility bottleneck (CLUB) model, which (i) provides a unified theoretical framework that generalizes most of the…
-
10 Feb 2022 1 repository listedWe present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning.
-
11 Oct 2021 1 repository listedTo this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism.
-
17 Aug 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Since our method reduces the cost for element-wise function computation, it is more efficient than existing cryptographic methods.
-
7 Jun 2021 1 repository listed Syntology official (archive's flag): 4 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate their effectiveness on standard benchmarks.
-
5 Jun 2021 1 repository listedWe study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer.
-
22 Apr 2021 1 repository listedWe then identify a sequence of "GPU-friendly" cryptographic protocols to enable privacy-preserving evaluation of both linear and non-linear operations on the GPU.
-
2 Mar 2021 1 repository listedDifferential Privacy (DP) is the leading approach to privacy preserving deep learning.
-
5 Oct 2020 1 repository listedWe study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
-
24 Sep 2020 1 repository listedIn the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data.
-
28 Jul 2020 1 repository listed Syntology 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer privacy for training data.
-
9 Jun 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)In this paper, we study the problem of node data privacy, where graph nodes have potentially sensitive data that is kept private, but they could be beneficial for a central server for training a GNN over the graph.
-
19 Feb 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)In this paper, we propose Fawkes, a system that helps individuals inoculate their images against unauthorized facial recognition models.
-
4 Jun 2019 1 repository listedThis problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to…
-
DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation29 Mar 2025 0 repositories listed
-
Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability10 Mar 2025 0 repositories listed
-
Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation19 Sep 2024 0 repositories listed
-
Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC24 Jul 2024 0 repositories listed
-
Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption15 Nov 2023 0 repositories listed
-
The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning9 Nov 2023 0 repositories listed
-
Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning9 Mar 2023 0 repositories listed
-
Training Differentially Private Graph Neural Networks with Random Walk Sampling2 Jan 2023 0 repositories listed
-
Privacy-preserving Deep Learning based Record Linkage3 Nov 2022 0 repositories listed
-
Review Learning: Alleviating Catastrophic Forgetting with Generative Replay without Generator17 Oct 2022 0 repositories listed
-
Privacy-Preserving Deep Learning Model for Covid-19 Disease Detection7 Sep 2022 0 repositories listed
-
Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approach15 Mar 2022 0 repositories listed
-
Communication-Efficient Federated Distillation with Active Data Sampling14 Mar 2022 0 repositories listed
-
DP-FP: Differentially Private Forward Propagation for Large Models29 Dec 2021 0 repositories listed
-
SoK: Privacy-preserving Deep Learning with Homomorphic Encryption23 Dec 2021 0 repositories listed
-
Towards a Privacy-preserving Deep Learning-based Network Intrusion Detection in Data Distribution Services12 Jun 2021 0 repositories listed
-
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models23 Feb 2021 0 repositories listed
-
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning26 Aug 2020 0 repositories listed
-
How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning18 Jul 2020 0 repositories listed
-
MPC Protocol for G-module and its Application in Secure Compare and ReLU8 Jul 2020 0 repositories listed
-
Security and Privacy Preserving Deep Learning23 Jun 2020 0 repositories listed
-
Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks20 Jun 2020 0 repositories listed
-
Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platforms9 Jan 2020 0 repositories listed
-
Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud18 Dec 2019 0 repositories listed
-
A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component21 Aug 2019 0 repositories listed
-
Private Deep Learning with Teacher Ensembles5 Jun 2019 0 repositories listed
-
Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning12 Apr 2019 0 repositories listed
-
Disguised-Nets: Image Disguising for Privacy-preserving Outsourced Deep Learning5 Feb 2019 0 repositories listed
-
Privacy-Preserving Deep Learning via Weight Transmission10 Sep 2018 0 repositories listed
Syntology lines on 8 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections