LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning

[2506.06742] LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2506.06742 (cs) [Submitted on 7 Jun 2025 ( v1 ), last revised 4 Sep 2025 (this version, v3)] Title: LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning Authors: Zeyu Yan , Yanfei Yao , Xuanbing Wen , Shixiong Zhang , Juli Zhang , Kai Fan View a PDF of the paper titled LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning, by Zeyu Yan and 5 other authors View PDF HTML (experimental) Abstract: Vertical Federated Learning (VFL) has emerged as a promising paradigm for collaborative model training across distributed feature spaces, which enables privacy-preserving learning without sharing raw data. However, recent studies have confirmed the feasibility of label inference attacks by internal adversaries. By strategically exploiting gradient vectors and semantic embeddings, attackers-through passive, active, or direct attacks-can accurately reconstruct private labels, leading to catastrophic data leakage. Existing defenses, which typically address isolated leakage vectors or are designed for specific types of attacks, remain vulnerable to emerging hybrid attacks that exploit multiple pathways simultaneously. To bridge this gap, we propose Label-Anonymized Defense with Substitution Gradient (LADSG), a unified and lightweight defense framework for VFL. LADSG first anonymizes true labels via soft distillation to reduce semantic exposure, then generates semantically-aligned substitute gradients to disrupt gradient-based leakage, and finally filters anomalous updates through gradient norm detection. It is scalable and compatible with standard VFL pipelines. Extensive experiments on six real-world datasets show that LADSG reduces the success rates of all three types of label inference attacks by 30-60% with minimal computational overhead, demonstrating its practical effectiveness. Comments: 20 pages, 8 figures Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2506.06742 [cs.CR] (or arXiv:2506.06742v3 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2506.06742 Focus to learn more arXiv-issued DOI via DataCite Journal reference: In Collaborative Computing: Networking, Applications and Worksharing. CollaborateCom 2025, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 681, Springer, Cham, 2026 Related DOI : https://doi.org/10.1007/978-3-032-21171-2_11 Focus to learn more DOI(s) linking to related resources Submission history From: Zeyu Yan [ view email ] [v1] Sat, 7 Jun 2025 10:10:56 UTC (3,995 KB) [v2] Tue, 5 Aug 2025 09:48:49 UTC (4,661 KB) [v3] Thu, 4 Sep 2025 15:43:39 UTC (4,659 KB) Full-text links: Access Paper: View a PDF of the paper titled LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning, by Zeyu Yan and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2025-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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

• Turning Privacy-preserving Mechanisms against Federated Learning#177333
• Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage#177295
• TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning#341905
• AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning#1104397
• Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge#13984