Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation

• URL: http://arxiv.org/abs/2503.16542v1
• Date: Wed, 19 Mar 2025 01:53:23 GMT
• Title: Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
• Authors: Shiyi Jiang, Farshad Firouzi, Krishnendu Chakrabarty,
• Abstract summary: We present a defense against gradient inversion attacks in federated learning.<n>Our approach can outperform the baselines with a reduction of 12.5% in the attacker's accuracy in classifying reconstructed images.<n>Results suggest the potential of a generalizable defense for healthcare data.
• Score: 3.5280398899666903
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient identification issues. Privacy-preserving machine learning (PPML) and privacy-enhancing technologies, particularly federated learning (FL), have emerged in recent years as innovative solutions to balance privacy protection with data utility; however, they also suffer from inherent privacy vulnerabilities. Gradient inversion attacks constitute major threats to data sharing in federated learning. Researchers have proposed many defenses against gradient inversion attacks. However, current defense methods for healthcare data lack generalizability, i.e., existing solutions may not be applicable to data from a broader range of populations. In addition, most existing defense methods are tested using non-healthcare data, which raises concerns about their applicability to real-world healthcare systems. In this study, we present a defense against gradient inversion attacks in federated learning. We achieve this using latent data perturbation and minimax optimization, utilizing both general and medical image datasets. Our method is compared to two baselines, and the results show that our approach can outperform the baselines with a reduction of 12.5% in the attacker's accuracy in classifying reconstructed images. The proposed method also yields an increase of over 12.4% in Mean Squared Error (MSE) between the original and reconstructed images at the same level of model utility of around 90% client classification accuracy. The results suggest the potential of a generalizable defense for healthcare data.

Related papers

• Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking [24.850260039814774]
  Fears of unauthorized use, like training commercial AI models, hinder researchers from sharing their valuable datasets. We propose the Sparsity-Aware Local Masking (SALM) method, which selectively perturbs significant pixel regions rather than the entire image. Our experiments demonstrate that SALM effectively prevents unauthorized training of different models and outperforms previous SoTA data protection methods.
  arXiv  Detail & Related papers  (2024-03-15T02:35:36Z)
• Reconciling AI Performance and Data Reconstruction Resilience for Medical Imaging [52.578054703818125]
  Artificial Intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive. Differential Privacy (DP) aims to circumvent these susceptibilities by setting a quantifiable privacy budget. We show that using very large privacy budgets can render reconstruction attacks impossible, while drops in performance are negligible.
  arXiv  Detail & Related papers  (2023-12-05T12:21:30Z)
• Privacy-Preserving Medical Image Classification through Deep Learning and Matrix Decomposition [0.0]
  Deep learning (DL) solutions have been extensively researched in the medical domain in recent years. The usage of health-related data is strictly regulated, processing medical records outside the hospital environment demands robust data protection measures. In this paper, we use singular value decomposition (SVD) and principal component analysis (PCA) to obfuscate the medical images before employing them in the DL analysis. The capability of DL algorithms to extract relevant information from secured data is assessed on a task of angiographic view classification based on obfuscated frames.
  arXiv  Detail & Related papers  (2023-08-31T08:21:09Z)
• Blockchain-empowered Federated Learning for Healthcare Metaverses: User-centric Incentive Mechanism with Optimal Data Freshness [66.3982155172418]
  We first design a user-centric privacy-preserving framework based on decentralized Federated Learning (FL) for healthcare metaverses. We then utilize Age of Information (AoI) as an effective data-freshness metric and propose an AoI-based contract theory model under Prospect Theory (PT) to motivate sensing data sharing.
  arXiv  Detail & Related papers  (2023-07-29T12:54:03Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging [47.99192239793597]
  We evaluated the effect of privacy-preserving training of AI models regarding accuracy and fairness compared to non-private training. Our study shows that -- under the challenging realistic circumstances of a real-life clinical dataset -- the privacy-preserving training of diagnostic deep learning models is possible with excellent diagnostic accuracy and fairness.
  arXiv  Detail & Related papers  (2023-02-03T09:49:13Z)
• Homomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Case [0.41998444721319217]
  This paper proposes a privacy-preserving federated learning algorithm for medical data using homomorphic encryption. The proposed algorithm uses a secure multi-party computation protocol to protect the deep learning model from the adversaries.
  arXiv  Detail & Related papers  (2022-04-16T08:38:35Z)
• When Accuracy Meets Privacy: Two-Stage Federated Transfer Learning Framework in Classification of Medical Images on Limited Data: A COVID-19 Case Study [77.34726150561087]
  COVID-19 pandemic has spread rapidly and caused a shortage of global medical resources. CNN has been widely utilized and verified in analyzing medical images.
  arXiv  Detail & Related papers  (2022-03-24T02:09:41Z)
• Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT data [5.582293277542012]
  In this work, we propose proximal gradient split learning (PSGL) method for defense against the model inversion attacks. We propose the use of proximal gradient method to recover gradient maps and a decision-level fusion strategy to improve the recognition performance.
  arXiv  Detail & Related papers  (2022-01-12T17:01:19Z)
• FLOP: Federated Learning on Medical Datasets using Partial Networks [84.54663831520853]
  COVID-19 Disease due to the novel coronavirus has caused a shortage of medical resources. Different data-driven deep learning models have been developed to mitigate the diagnosis of COVID-19. The data itself is still scarce due to patient privacy concerns. We propose a simple yet effective algorithm, named textbfFederated textbfL textbfon Medical datasets using textbfPartial Networks (FLOP)
  arXiv  Detail & Related papers  (2021-02-10T01:56:58Z)
• Privacy-preserving medical image analysis [53.4844489668116]
  We present PriMIA, a software framework designed for privacy-preserving machine learning (PPML) in medical imaging. We show significantly better classification performance of a securely aggregated federated learning model compared to human experts on unseen datasets. We empirically evaluate the framework's security against a gradient-based model inversion attack.
  arXiv  Detail & Related papers  (2020-12-10T13:56:00Z)
• Evaluation of Inference Attack Models for Deep Learning on Medical Data [16.128164765752032]
  Recently developed inference attack algorithms indicate that images and text records can be reconstructed by malicious parties. This gives rise to the concern that medical images and electronic health records containing sensitive patient information are vulnerable to these attacks. This paper aims to attract interest from researchers in the medical deep learning community to this important problem.
  arXiv  Detail & Related papers  (2020-10-31T03:18:36Z)

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.