Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakage
Not on the map. Why?
Abstract (arXiv)
We propose Gradient Inversion Transcript (GIT), a novel generative approach for reconstructing training data from leaked gradients. GIT employs a generative attack model, whose architecture is tailored to align with the structure of the leaked model based on theoretical analysis. Once trained offline, GIT can be deployed efficiently and only relies on the leaked gradients to reconstruct the input data, rendering it applicable under various distributed learning environments. When used as a prior for other iterative optimization-based methods, GIT not only accelerates convergence but also enhances the overall reconstruction quality. GIT consistently outperforms existing methods across multiple datasets and demonstrates strong robustness under challenging conditions, including inaccurate gradients, data distribution shifts and discrepancies in model parameters.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 26 May 2025.
Builds on
21 of 32 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2016Deep Learning with Differential Privacycited by 2,728
- 2019Deep Leakage from Gradientscited by 1,021
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
- 2020iDLG: Improved Deep Leakage from Gradientscited by 382
- 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
- 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
- 2022Reconstructing Training Data from Trained Neural Networkscited by 133
- 2021Gradient Inversion with Generative Image Priorcited by 101
9 more
- 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
- 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
- 2020A Framework for Evaluating Gradient Leakage Attacks in Federated Learningcited by 64
- 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
- 2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
- 2020SAPAG: A Self-Adaptive Privacy Attack From Gradientscited by 27
- 2022Reconstructing Training Data from Model Gradient, Provablycited by 27
- 2024SPEAR:Exact Gradient Inversion of Batches in Federated Learningcited by 15
- 2024Recovering Labels from Local Updates in Federated Learningcited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.