SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks

• URL: http://arxiv.org/abs/2403.08481v1
• Date: Wed, 13 Mar 2024 12:46:51 GMT
• Title: SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks
• Authors: Guy Amit, Abigail Goldsteen, Ariel Farkash
• Abstract summary: 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.
• Score: 1.03590082373586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary datasets. This fine-tuning data is especially likely to contain personal or sensitive information about individuals, resulting in increased privacy risk. Membership inference attacks are the most commonly employed attack to assess the privacy leakage of a machine learning model. However, limited research is available on the factors that affect the vulnerability of language models to this kind of attack, or on the applicability of different defense strategies in the language domain. We provide the first systematic review of the vulnerability of fine-tuned large language models to membership inference attacks, the various factors that come into play, and the effectiveness of different defense strategies. 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.

Related papers

• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• 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)
• 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)
• Locally Differentially Private Document Generation Using Zero Shot Prompting [61.20953109732442]
  We propose a locally differentially private mechanism called DP-Prompt to counter author de-anonymization attacks. When DP-Prompt is used with a powerful language model like ChatGPT (gpt-3.5), we observe a notable reduction in the success rate of de-anonymization attacks.
  arXiv  Detail & Related papers  (2023-10-24T18:25:13Z)
• Improved Membership Inference Attacks Against Language Classification Models [0.0]
  We present a novel framework for running membership inference attacks against classification models. We show that this approach achieves higher accuracy than either a single attack model or an attack model per class label.
  arXiv  Detail & Related papers  (2023-10-11T06:09:48Z)
• 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)
• Can Language Models be Instructed to Protect Personal Information? [30.187731765653428]
  We introduce PrivQA -- a benchmark to assess the privacy/utility trade-off when a model is instructed to protect specific categories of personal information in a simulated scenario. We find that adversaries can easily circumvent these protections with simple jailbreaking methods through textual and/or image inputs. We believe PrivQA has the potential to support the development of new models with improved privacy protections, as well as the adversarial robustness of these protections.
  arXiv  Detail & Related papers  (2023-10-03T17:30:33Z)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)
• Defending against Reconstruction Attacks with R\'enyi Differential Privacy [72.1188520352079]
  Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. Differential privacy is a known solution to such attacks, but is often used with a relatively large privacy budget. We show that, for a same mechanism, we can derive privacy guarantees for reconstruction attacks that are better than the traditional ones from the literature.
  arXiv  Detail & Related papers  (2022-02-15T18:09:30Z)

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.