Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning

• URL: http://arxiv.org/abs/2411.14937v2
• Date: Sat, 02 Aug 2025 08:52:34 GMT
• Title: Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning
• Authors: Junjie Shan, Ziqi Zhao, Jialin Lu, Rui Zhang, Siu Ming Yiu, Ka-Ho Chow,
• Abstract summary: vision-language models (VLMs) can be weaponized to enhance gradient inversion attacks (GIAs) in federated learning (FL)<n>We propose Geminio, the first approach to transform GIAs into semantically meaningful, targeted attacks.<n>It enables a brand new privacy attack experience: attackers can describe, in natural language, the data they consider valuable, and Geminio will prioritize reconstruction to focus on those high-value samples.
• Score: 18.326636715274372
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models that bridge vision and language have made significant progress. While they have inspired many life-enriching applications, their potential for abuse in creating new threats remains largely unexplored. In this paper, we reveal that vision-language models (VLMs) can be weaponized to enhance gradient inversion attacks (GIAs) in federated learning (FL), where an FL server attempts to reconstruct private data samples from gradients shared by victim clients. Despite recent advances, existing GIAs struggle to reconstruct high-resolution images when the victim has a large local data batch. One promising direction is to focus reconstruction on valuable samples rather than the entire batch, but current methods lack the flexibility to target specific data of interest. To address this gap, we propose Geminio, the first approach to transform GIAs into semantically meaningful, targeted attacks. It enables a brand new privacy attack experience: attackers can describe, in natural language, the data they consider valuable, and Geminio will prioritize reconstruction to focus on those high-value samples. This is achieved by leveraging a pretrained VLM to guide the optimization of a malicious global model that, when shared with and optimized by a victim, retains only gradients of samples that match the attacker-specified query. Geminio can be launched at any FL round and has no impact on normal training (i.e., the FL server can steal clients' data while still producing a high-utility ML model as in benign scenarios). Extensive experiments demonstrate its effectiveness in pinpointing and reconstructing targeted samples, with high success rates across complex datasets and large batch sizes with resilience against defenses.

Related papers

• Deep Leakage with Generative Flow Matching Denoiser [54.05993847488204]
  We introduce a new deep leakage (DL) attack that integrates a generative Flow Matching (FM) prior into the reconstruction process.<n>Our approach consistently outperforms state-of-the-art attacks across pixel-level, perceptual, and feature-based similarity metrics.
  arXiv  Detail & Related papers  (2026-01-21T14:51:01Z)
• On the Detectability of Active Gradient Inversion Attacks in Federated Learning [5.828517827413101]
  Federated Learning (FL) can collaboratively train a Machine Learning (ML) model while keeping clients' data on-site.<n>However, prior studies have shown that gradients exchanged during the FL training remain vulnerable to Gradient Inversion Attacks (GIAs)<n>These attacks allow reconstructing the clients' local data, breaking the privacy promise of FL.<n>Recent, novel active GIAs have emerged, claiming to be far stealthier than previous approaches.
  arXiv  Detail & Related papers  (2025-11-13T17:06:57Z)
• Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning [10.145100498980346]
  Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data.<n>Recent studies have revealed critical vulnerabilities in FL, showing that a malicious central server can manipulate model updates to reconstruct clients' private data.<n>We introduce a novel data reconstruction attack that overcomes these limitations.
  arXiv  Detail & Related papers  (2025-05-15T13:16:32Z)
• Attribute Inference Attacks for Federated Regression Tasks [14.152503562997662]
  Federated Learning (FL) enables clients to collaboratively train a global machine learning model while keeping their data localized. Recent studies have revealed that the training phase of FL is vulnerable to reconstruction attacks. We propose novel model-based AIAs specifically designed for regression tasks in FL environments.
  arXiv  Detail & Related papers  (2024-11-19T18:06:06Z)
• GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search [52.27057178618773]
  Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients.<n>A majority of gradient inversion methods rely heavily on explicit prior knowledge, which is often unavailable in realistic scenarios.<n>We propose Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures.
  arXiv  Detail & Related papers  (2024-05-31T09:29:43Z)
• GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge [4.839514405631815]
  Federated learning (FL) has emerged as a privacy-preserving machine learning approach. gradient inversion attacks can exploit the gradients of FL to recreate the original user data. We propose a novel Gradient Inversion attack based on Style Migration Network (GI-SMN)
  arXiv  Detail & Related papers  (2024-05-06T14:29:24Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• 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)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• On Evaluating Adversarial Robustness of Large Vision-Language Models [64.66104342002882]
  We evaluate the robustness of large vision-language models (VLMs) in the most realistic and high-risk setting. In particular, we first craft targeted adversarial examples against pretrained models such as CLIP and BLIP. Black-box queries on these VLMs can further improve the effectiveness of targeted evasion.
  arXiv  Detail & Related papers  (2023-05-26T13:49:44Z)
• Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network [102.21368201494909]
  Model inversion (MI) attacks have raised increasing concerns about privacy. Recent MI attacks leverage a generative adversarial network (GAN) as an image prior to narrow the search space. We propose Pseudo Label-Guided MI (PLG-MI) attack via conditional GAN (cGAN)
  arXiv  Detail & Related papers  (2023-02-20T07:29:34Z)
• Concealing Sensitive Samples against Gradient Leakage in Federated Learning [41.43099791763444]
  Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Recent studies expose the vulnerability of FL to model inversion attacks, where adversaries reconstruct users private data via eavesdropping on the shared gradient information. We present a simple, yet effective defense strategy that obfuscates the gradients of the sensitive data with concealed samples.
  arXiv  Detail & Related papers  (2022-09-13T04:19:35Z)
• 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)
• Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification [65.33308059737506]
  Federated learning (FL) has rapidly risen in popularity due to its promise of privacy and efficiency. Previous works have exposed privacy vulnerabilities in the FL pipeline by recovering user data from gradient updates. We introduce a new strategy that dramatically elevates existing attacks to operate on batches of arbitrarily large size.
  arXiv  Detail & Related papers  (2022-02-01T17:26:11Z)
• A Novel Attribute Reconstruction Attack in Federated Learning [7.426857207652392]
  Federated learning (FL) emerged as a promising learning paradigm to enable a multitude of participants to construct a joint ML model without exposing their private training data. Existing FL designs have been shown to exhibit vulnerabilities which can be exploited by adversaries both within and outside of the system to compromise data privacy. We develop a more effective and efficient gradient matching based method called cos-matching to reconstruct the training data attributes.
  arXiv  Detail & Related papers  (2021-08-16T05:57:01Z)
• Knowledge-Enriched Distributional Model Inversion Attacks [49.43828150561947]
  Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data. Our experiments show that the combination of these techniques can significantly boost the success rate of the state-of-the-art MI attacks by 150%.
  arXiv  Detail & Related papers  (2020-10-08T16:20:48Z)

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.