The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning

• URL: http://arxiv.org/abs/2502.04106v1
• Date: Thu, 06 Feb 2025 14:31:14 GMT
• Title: The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning
• Authors: Kunlan Xiang, Haomiao Yang, Meng Hao, Haoxin Wang, Shaofeng Li, Zikang Ding, Tianwei Zhang,
• Abstract summary: In Federated Learning (FL), clients share gradients with a central server while keeping their data local. malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing significant privacy risks. We introduce a new theoretical analysis approach, which uniformly models AGLAs as backdoor poisoning. We propose Enhanced Gradient Global Vulnerability (EGGV), the first AGLA that achieves complete attack coverage while evading client-side detection.
• Score: 14.424323591908939
• License:
• Abstract: In Federated Learning (FL), clients share gradients with a central server while keeping their data local. However, malicious servers could deliberately manipulate the models to reconstruct clients' data from shared gradients, posing significant privacy risks. Although such active gradient leakage attacks (AGLAs) have been widely studied, they suffer from several limitations including incomplete attack coverage and poor stealthiness. In this paper, we address these limitations with two core contributions. First, we introduce a new theoretical analysis approach, which uniformly models AGLAs as backdoor poisoning. This analysis approach reveals that the core principle of AGLAs is to bias the gradient space to prioritize the reconstruction of a small subset of samples while sacrificing the majority, which theoretically explains the above limitations of existing AGLAs. Second, we propose Enhanced Gradient Global Vulnerability (EGGV), the first AGLA that achieves complete attack coverage while evading client-side detection. In particular, EGGV employs a gradient projector and a jointly optimized discriminator to assess gradient vulnerability, steering the gradient space toward the point most prone to data leakage. Extensive experiments show that EGGV achieves complete attack coverage and surpasses SOTA with at least a 43% increase in reconstruction quality (PSNR) and a 45% improvement in stealthiness (D-SNR).

Related papers

• CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling [63.07948989346385]
  Federated learning collaboratively trains a neural network on a global server. Each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. Existing gradient inversion attacks can exploit this vulnerability to recover private training instances from a client's gradient vectors. We present a novel defense tailored for large neural network models.
  arXiv  Detail & Related papers  (2025-01-27T01:06:23Z)
• Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning [21.892850886276317]
  gradient purification defense, named GPD, integrates seamlessly with existing DFL aggregation to defend against poisoning attacks. It aims to mitigate the harm in model gradients while retaining the benefit in model weights for enhancing accuracy. It significantly outperforms state-of-the-art defenses in terms of accuracy against various poisoning attacks.
  arXiv  Detail & Related papers  (2025-01-08T12:14:00Z)
• Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning [11.18348760596715]
  Federated Learning exhibits privacy vulnerabilities under gradient inversion attacks (GIAs) We propose a stealthy label inference attack to bypass Secure Aggregation (SA) and recover individual clients' private labels. Our attack achieves large-scale label recovery with 100% accuracy on various datasets and model architectures.
  arXiv  Detail & Related papers  (2024-06-22T04:42:18Z)
• Rethinking PGD Attack: Is Sign Function Necessary? [131.6894310945647]
  We present a theoretical analysis of how such sign-based update algorithm influences step-wise attack performance. We propose a new raw gradient descent (RGD) algorithm that eliminates the use of sign. The effectiveness of the proposed RGD algorithm has been demonstrated extensively in experiments.
  arXiv  Detail & Related papers  (2023-12-03T02:26:58Z)
• A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer [11.770915202449517]
  The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This research presents a comprehensive analysis of the gradient leakage method when applied specifically to transformer-based models.
  arXiv  Detail & Related papers  (2023-11-22T09:58:01Z)
• Understanding Deep Gradient Leakage via Inversion Influence Functions [53.1839233598743]
  Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. We propose a novel Inversion Influence Function (I$2$F) that establishes a closed-form connection between the recovered images and the private gradients. We empirically demonstrate that I$2$F effectively approximated the DGL generally on different model architectures, datasets, attack implementations, and perturbation-based defenses.
  arXiv  Detail & Related papers  (2023-09-22T17:26:24Z)
• Client-side Gradient Inversion Against Federated Learning from Poisoning [59.74484221875662]
  Federated Learning (FL) enables distributed participants to train a global model without sharing data directly to a central server. Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples. We propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients.
  arXiv  Detail & Related papers  (2023-09-14T03:48:27Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• Discriminator-Free Generative Adversarial Attack [87.71852388383242]
  Agenerative-based adversarial attacks can get rid of this limitation. ASymmetric Saliency-based Auto-Encoder (SSAE) generates the perturbations. The adversarial examples generated by SSAE not only make thewidely-used models collapse, but also achieves good visual quality.
  arXiv  Detail & Related papers  (2021-07-20T01:55:21Z)
• Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks [3.055601224691843]
  The vulnerability of deep neural networks to small and even imperceptible perturbations has become a central topic in deep learning research. We propose Dynamically Dynamically Nonlocal Gradient Descent (DSNGD) as a vulnerability defense mechanism. We show that DSNGD-based attacks are average 35% faster while achieving 0.9% to 27.1% higher success rates compared to their gradient descent-based counterparts.
  arXiv  Detail & Related papers  (2020-11-05T08:55:24Z)

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.