GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models

[2510.17621] GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models Skip to main content Search Submit Donate Log in Computer Science > Cryptography and Security arXiv:2510.17621 (cs) [Submitted on 20 Oct 2025 ( v1 ), last revised 23 Oct 2025 (this version, v2)] Title: GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models Authors: Vincenzo Carletti , Pasquale Foggia , Carlo Mazzocca , Giuseppe Parrella , Mario Vento View PDF HTML (experimental) Abstract: Federated Learning (FL) enables collaborative training of Machine Learning (ML) models across multiple clients while preserving their privacy. Rather than sharing raw data, federated clients transmit locally computed updates to train the global model. Although this paradigm should provide stronger privacy guarantees than centralized ML, client updates remain vulnerable to privacy leakage. Adversaries can exploit them to infer sensitive properties about the training data or even to reconstruct the original inputs via Gradient Inversion Attacks (GIAs). Under the honest-butcurious threat model, GIAs attempt to reconstruct training data by reversing intermediate updates using optimizationbased techniques. We observe that these approaches usually reconstruct noisy approximations of the original inputs, whose quality can be enhanced with specialized denoising models. This paper presents Gradient Update Inversion with DEnoising (GUIDE), a novel methodology that leverages diffusion models as denoising tools to improve image reconstruction attacks in FL. GUIDE can be integrated into any GIAs that exploits surrogate datasets, a widely adopted assumption in GIAs literature. We comprehensively evaluate our approach in two attack scenarios that use different FL algorithms, models, and datasets. Our results demonstrate that GUIDE integrates seamlessly with two state-ofthe- art GIAs, substantially improving reconstruction quality across multiple metrics. Specifically, GUIDE achieves up to 46% higher perceptual similarity, as measured by the DreamSim metric. Comments: This work has been submitted to the IEEE for possible publication Subjects: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2510.17621 [cs.CR] (or arXiv:2510.17621v2 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2510.17621 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.1109/JIOT.2026.3726586 Focus to learn more DOI(s) linking to related resources Submission history From: Giuseppe Parrella [ view email ] [v1] Mon, 20 Oct 2025 15:04:29 UTC (18,239 KB) [v2] Thu, 23 Oct 2025 09:28:35 UTC (18,304 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2025-10 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models#670407
• Enhanced Security and Privacy via Fragmented Federated Learning#400577
• Federated Learning With Sparsified Model Perturbation: Improving Accuracy Under Client-Level Differential Privacy#177325
• Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning#987991
• FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning#1061591