Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning

• URL: http://arxiv.org/abs/2312.05720v4
• Date: Fri, 15 Mar 2024 18:23:05 GMT
• Title: Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning
• Authors: Jianwei Li, Sheng Liu, Qi Lei,
• Abstract summary: This paper presents a two-stage privacy attack strategy that targets the vulnerabilities in the architecture of contemporary language models. Our comparative experiments demonstrate superior attack performance across various datasets and scenarios. We call for the community to recognize and address these potential privacy risks in designing large language models.
• Score: 24.059033969435973
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Language models trained via federated learning (FL) demonstrate impressive capabilities in handling complex tasks while protecting user privacy. Recent studies indicate that leveraging gradient information and prior knowledge can potentially reveal training samples within FL setting. However, these investigations have overlooked the potential privacy risks tied to the intrinsic architecture of the models. This paper presents a two-stage privacy attack strategy that targets the vulnerabilities in the architecture of contemporary language models, significantly enhancing attack performance by initially recovering certain feature directions as additional supervisory signals. Our comparative experiments demonstrate superior attack performance across various datasets and scenarios, highlighting the privacy leakage risk associated with the increasingly complex architectures of language models. We call for the community to recognize and address these potential privacy risks in designing large language models.

Related papers

• New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook [54.24701201956833]
  Security and privacy issues have undermined users' confidence in pre-trained models. Current literature lacks a clear taxonomy of emerging attacks and defenses for pre-trained models. This taxonomy categorizes attacks and defenses into No-Change, Input-Change, and Model-Change approaches.
  arXiv  Detail & Related papers  (2024-11-12T10:15:33Z)
• 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)
• Unique Security and Privacy Threats of Large Language Model: A Comprehensive Survey [46.19229410404056]
  Large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and generation capabilities. Privacy and security issues have been revealed throughout their life cycle.
  arXiv  Detail & Related papers  (2024-06-12T07:55:32Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks [1.03590082373586]
  We provide the first systematic review of the vulnerability of large language models to membership inference attacks. We find that some training methods provide significantly reduced privacy risk, with the combination of differential privacy and low-rank adaptors achieving the best privacy protection against these attacks.
  arXiv  Detail & Related papers  (2024-03-13T12:46:51Z)
• Membership Inference Attacks and Privacy in Topic Modeling [3.503833571450681]
  We propose an attack against topic models that can confidently identify members of the training data. We propose a framework for private topic modeling that incorporates DP vocabulary selection as a pre-processing step.
  arXiv  Detail & Related papers  (2024-03-07T12:43:42Z)
• Privacy in Large Language Models: Attacks, Defenses and Future Directions [84.73301039987128]
  We analyze the current privacy attacks targeting large language models (LLMs) and categorize them according to the adversary's assumed capabilities. We present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks.
  arXiv  Detail & Related papers  (2023-10-16T13:23:54Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)

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.