MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning

• URL: http://arxiv.org/abs/2608.01521v1
• Date: Sun, 02 Aug 2026 22:18:34 GMT
• Title: MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning
• Abstract summary: We propose an analytical attack that enables a malicious server to recover private user data by leveraging a pretrained model and fine-tuning parameters.<n>Unlike prior works, our attack is applicable to both language and vision tasks, does not rely on computationally expensive (adversarial) pretraining with public datasets or require the number of training tokens to be less than the rank of LoRA modules.
• Score: 11.852406625172216
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parameter-efficient fine-tuning (PEFT), such as low-rank adaptation (LoRA), has recently been adopted in federated learning to reduce communication and computation costs. In this setup, users download a pretrained model from the server prior to fine-tuning, and then fine-tune lightweight LoRA modules locally while keeping the pretrained model frozen, sharing only the gradients of the fine-tuning parameters with the server. Despite its growing popularity, robustness of federated fine-tuning against an adversarial server remains underexplored, where the server maliciously tampers with the training protocol to breach the privacy of users' data. In this work, we investigate gradient inversion attacks on LoRA fine-tuning. We propose an analytical attack that enables a malicious server to recover private user data by leveraging a poisoned pretrained model and fine-tuning parameters. Our design embeds fine-tuning data within the shared gradients, to allow the server to analytically reconstruct user data. Unlike prior works, our attack is applicable to both language and vision tasks, does not rely on computationally expensive (adversarial) pretraining with public datasets or require the number of training tokens to be less than the rank of LoRA modules. Experimental results on both language and vision tasks demonstrate high-fidelity data recovery across multiple baselines, revealing several critical vulnerabilities.

Related papers

• Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning [25.434223317282274]
  Federated learning (FL) allows multiple data-owners to collaboratively train machine learning models by exchanging local gradients.<n>Recently, parameter-efficient fine-tuning (PEFT) of large-scale pretrained models has gained substantial attention in FL.<n>We investigate how the privacy of the fine-tuning data of the users can be compromised via a malicious design of the pretrained model and trainable adapter modules.
  arXiv  Detail & Related papers  (2025-06-04T21:14:21Z)
• FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates [58.18162789618869]
  Federated Learning (FL) is a widely used framework for training models in a decentralized manner.<n>We propose the FedRand framework, which avoids disclosing the full set of client parameters.<n>We empirically validate that FedRand improves robustness against MIAs compared to relevant baselines.
  arXiv  Detail & Related papers  (2025-03-10T11:55:50Z)
• Safely Learning with Private Data: A Federated Learning Framework for Large Language Model [3.1077263218029105]
  Federated learning (FL) is an ideal solution for training models with distributed private data.<n>Traditional frameworks like FedAvg are unsuitable for large language models (LLM)<n>We propose FL-GLM, which prevents data leakage caused by both server-side and peer-client attacks.
  arXiv  Detail & Related papers  (2024-06-21T06:43:15Z)
• A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning [14.110303634976272]
  Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving features and minimal computational requirements.<n>Previous research consistently highlights the potential privacy breaches in SL systems by server adversaries reconstructing training data.<n>This paper introduces a new semi-honest Data Reconstruction Attack on SL, named Feature-Oriented Reconstruction Attack (FORA)
  arXiv  Detail & Related papers  (2024-05-07T08:38:35Z)
• Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks [48.70867241987739]
  InferGuard is a novel Byzantine-robust aggregation rule aimed at defending against client-side training data distribution inference attacks. The results of our experiments indicate that our defense mechanism is highly effective in protecting against client-side training data distribution inference attacks.
  arXiv  Detail & Related papers  (2024-03-05T17:41:35Z)
• Blockchain-enabled Trustworthy Federated Unlearning [50.01101423318312]
  Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients. Existing works require central servers to retain the historical model parameters from distributed clients. This paper proposes a new blockchain-enabled trustworthy federated unlearning framework.
  arXiv  Detail & Related papers  (2024-01-29T07:04:48Z)
• 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)
• BAFFLE: A Baseline of Backpropagation-Free Federated Learning [71.09425114547055]
  Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. We develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation is replaced by multiple forward processes to estimate gradients. BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments.
  arXiv  Detail & Related papers  (2023-01-28T13:34:36Z)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• When the Curious Abandon Honesty: Federated Learning Is Not Private [36.95590214441999]
  In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. We show a novel data reconstruction attack which allows an active and dishonest central party to efficiently extract user data from the received gradients.
  arXiv  Detail & Related papers  (2021-12-06T10:37:03Z)
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning [14.134217287912008]
  Federated learning (FL) is an emerging distributed machine learning framework for collaborative model training with a network of clients. Recent studies have shown that even sharing local parameter updates from a client to the federated server may be susceptible to gradient leakage attacks. We present a principled framework for evaluating and comparing different forms of client privacy leakage attacks.
  arXiv  Detail & Related papers  (2020-04-22T05:15:03Z)

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.