Quantifying and Defending against the Privacy Risk in Logit-based Federated Learning

• URL: http://arxiv.org/abs/2606.08252v1
• Date: Sat, 06 Jun 2026 16:40:53 GMT
• Title: Quantifying and Defending against the Privacy Risk in Logit-based Federated Learning
• Abstract summary: Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among clients.<n>Logit-based FL approaches share model outputs (logits) on public data.<n>This research presents the first theoretical and empirical analysis of a hidden privacy risk in logit-based FL methods.
• Score: 20.9174755182923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among clients. Unlike traditional parameter-based FL methods that exchange model weights or gradients during training, emerging logit-based FL approaches share model outputs (logits) on public data. This strategy promotes model heterogeneity, reduces communication overhead, and enhances clients' privacy. However, the potential privacy risks associated with these logit-based methods have been largely overlooked. This research presents the first theoretical and empirical analysis of a hidden privacy risk in logit-based FL methods - the risk that a semi-honest server (adversary) may learn clients' private models from logits. To quantify and address this threat, we develop the Adaptive Model Stealing Attack (AdaMSA) by leveraging historical logits during training. Notably, we observe that this inherent privacy risk persists even when public data is unrelated to private data, emphasizing the urgency to address privacy vulnerabilities in logit-based FL methods. Moreover, our theoretical analysis establishes the bounds of this privacy risk. We then propose a simple but effective defense strategy that perturbs the transmitted logits in the direction that minimizes the privacy risk while maximally preserving the training performance. The experimental results validate our analysis and demonstrate the effectiveness of AdaMSA and our defense strategy.

Related papers

• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• Enhancing Model Privacy in Federated Learning with Random Masking and Quantization [46.915409150222494]
  The rise of large language models (LLMs) has introduced new challenges in distributed systems.<n>This highlights the need for a federated learning approach that can safeguard both sensitive data and proprietary models.<n>We propose FedQSN, a federated learning approach that leverages random masking to obscure a subnetwork of model parameters.
  arXiv  Detail & Related papers  (2025-08-26T10:34:13Z)
• FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning [17.853502904387376]
  Federated Learning (FL) enables collaborative training of models across distributed clients without sharing local data, addressing privacy concerns in decentralized systems.<n>We propose Federated Error Minimization (FedEM), a novel algorithm that incorporates controlled perturbations through adaptive noise injection.<n> Experimental results on benchmark datasets demonstrate that FedEM significantly reduces privacy risks and preserves model accuracy, achieving a robust balance between privacy protection and utility preservation.
  arXiv  Detail & Related papers  (2025-03-08T02:48:00Z)
• Privacy Attack in Federated Learning is Not Easy: An Experimental Study [5.065947993017158]
  Federated learning (FL) is an emerging distributed machine learning paradigm proposed for privacy preservation. Recent studies have indicated that FL cannot entirely guarantee privacy protection. It remains uncertain whether privacy attack FL algorithms are effective in realistic federated environments.
  arXiv  Detail & Related papers  (2024-09-28T10:06:34Z)
• Defending against Data Poisoning Attacks in Federated Learning via User Elimination [0.0]
  This paper introduces a novel framework focused on the strategic elimination of adversarial users within a federated model. We detect anomalies in the aggregation phase of the Federated Algorithm, by integrating metadata gathered by the local training instances with Differential Privacy techniques. Our experiments demonstrate the efficacy of our methods, significantly mitigating the risk of data poisoning while maintaining user privacy and model performance.
  arXiv  Detail & Related papers  (2024-04-19T10:36:00Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Active Membership Inference Attack under Local Differential Privacy in Federated Learning [18.017082794703555]
  Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection. We propose a new active membership inference (AMI) attack carried out by a dishonest server in FL.
  arXiv  Detail & Related papers  (2023-02-24T15:21:39Z)
• Do Gradient Inversion Attacks Make Federated Learning Unsafe? [70.0231254112197]
  Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. Recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in real FL use-cases and provide a new baseline attack.
  arXiv  Detail & Related papers  (2022-02-14T18:33:12Z)
• Distributed Machine Learning and the Semblance of Trust [66.1227776348216]
  Federated Learning (FL) allows the data owner to maintain data governance and perform model training locally without having to share their data. FL and related techniques are often described as privacy-preserving. We explain why this term is not appropriate and outline the risks associated with over-reliance on protocols that were not designed with formal definitions of privacy in mind.
  arXiv  Detail & Related papers  (2021-12-21T08:44:05Z)
• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy [67.4471689755097]
  This paper empirically demonstrates that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity. We provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates.
  arXiv  Detail & Related papers  (2021-06-25T14:47:19Z)
• Systematic Evaluation of Privacy Risks of Machine Learning Models [41.017707772150835]
  We show that prior work on membership inference attacks may severely underestimate the privacy risks. We first propose to benchmark membership inference privacy risks by improving existing non-neural network based inference attacks. We then introduce a new approach for fine-grained privacy analysis by formulating and deriving a new metric called the privacy risk score.
  arXiv  Detail & Related papers  (2020-03-24T00:53:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.