Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models

• URL: http://arxiv.org/abs/2506.06060v1
• Date: Fri, 06 Jun 2025 13:13:29 GMT
• Title: Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
• Authors: Yingqi Hu, Zhuo Zhang, Jingyuan Zhang, Lizhen Qu, Zenglin Xu,
• Abstract summary: Federated fine-tuning of large language models (FedLLMs) presents a promising approach for achieving strong model performance while preserving data privacy in sensitive domains.<n>We introduce simple yet effective extraction attack algorithms specifically designed for FedLLMs.<n> Experimental results show that our method can extract up to 56.57% of victim-exclusive PII, with "Address," "Birthday," and "Name" being the most vulnerable categories.
• Score: 34.4473331513019
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated fine-tuning of large language models (FedLLMs) presents a promising approach for achieving strong model performance while preserving data privacy in sensitive domains. However, the inherent memorization ability of LLMs makes them vulnerable to training data extraction attacks. To investigate this risk, we introduce simple yet effective extraction attack algorithms specifically designed for FedLLMs. In contrast to prior "verbatim" extraction attacks, which assume access to fragments from all training data, our approach operates under a more realistic threat model, where the attacker only has access to a single client's data and aims to extract previously unseen personally identifiable information (PII) from other clients. This requires leveraging contextual prefixes held by the attacker to generalize across clients. To evaluate the effectiveness of our approaches, we propose two rigorous metrics-coverage rate and efficiency-and extend a real-world legal dataset with PII annotations aligned with CPIS, GDPR, and CCPA standards, achieving 89.9% human-verified precision. Experimental results show that our method can extract up to 56.57% of victim-exclusive PII, with "Address," "Birthday," and "Name" being the most vulnerable categories. Our findings underscore the pressing need for robust defense strategies and contribute a new benchmark and evaluation framework for future research in privacy-preserving federated learning.

Related papers

• Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning [4.275908952997288]
  Federated Learning (FL) is a collaborative learning framework designed to protect client data.<n>Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to model extraction attacks.<n>This paper examines the vulnerability of FL-based victim models to two types of model extraction attacks.
  arXiv  Detail & Related papers  (2025-05-25T22:40:10Z)
• No Query, No Access [50.18709429731724]
  We introduce the textbfVictim Data-based Adrial Attack (VDBA), which operates using only victim texts.<n>To prevent access to the victim model, we create a shadow dataset with publicly available pre-trained models and clustering methods.<n>Experiments on the Emotion and SST5 datasets show that VDBA outperforms state-of-the-art methods, achieving an ASR improvement of 52.08%.
  arXiv  Detail & Related papers  (2025-05-12T06:19:59Z)
• Privacy-Preserved Automated Scoring using Federated Learning for Educational Research [1.2556373621040728]
  We propose a federated learning (FL) framework for automated scoring of educational assessments.<n>We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline.<n>Results show that our model achieves the highest accuracy (94.5%) among FL approaches.
  arXiv  Detail & Related papers  (2025-03-12T19:06:25Z)
• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
  Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models. This paper proposes a framework composed of three LLM-based components -- a privacy evaluator, a utility evaluator, and an optimization component.
  arXiv  Detail & Related papers  (2024-07-16T14:28:56Z)
• Federated Face Forgery Detection Learning with Personalized Representation [63.90408023506508]
  Deep generator technology can produce high-quality fake videos that are indistinguishable, posing a serious social threat. Traditional forgery detection methods directly centralized training on data. The paper proposes a novel federated face forgery detection learning with personalized representation.
  arXiv  Detail & Related papers  (2024-06-17T02:20:30Z)
• 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)
• 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)
• 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)
• 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)
• FedCC: Robust Federated Learning against Model Poisoning Attacks [0.0]
  Federated learning is a distributed framework designed to address privacy concerns.<n>It introduces new attack surfaces, which are especially prone when data is non-Independently and Identically Distributed.<n>We present FedCC, a simple yet effective novel defense algorithm against model poisoning attacks.
  arXiv  Detail & Related papers  (2022-12-05T01:52:32Z)
• Privacy-Preserving Federated Learning on Partitioned Attributes [6.661716208346423]
  Federated learning empowers collaborative training without exposing local data or models. We introduce an adversarial learning based procedure which tunes a local model to release privacy-preserving intermediate representations. To alleviate the accuracy decline, we propose a defense method based on the forward-backward splitting algorithm.
  arXiv  Detail & Related papers  (2021-04-29T14:49:14Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)
• SPEED: Secure, PrivatE, and Efficient Deep learning [2.283665431721732]
  We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-16T19:31:52Z)

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.