Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

• URL: http://arxiv.org/abs/2404.01231v1
• Date: Mon, 1 Apr 2024 16:50:54 GMT
• Title: Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
• Authors: Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini,
• Abstract summary: 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.
• Score: 112.48136829374741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the vulnerability to backdoor attacks. In this paper, we unveil a new vulnerability: the privacy backdoor attack. This black-box privacy attack aims to amplify the privacy leakage that arises when fine-tuning a model: 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. We conduct extensive experiments on various datasets and models, including both vision-language models (CLIP) and large language models, demonstrating the broad applicability and effectiveness of such an attack. Additionally, we carry out multiple ablation studies with different fine-tuning methods and inference strategies to thoroughly analyze this new threat. 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.

Related papers

• Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage [12.892449128678516]
  Fine-tuning language models on private data for downstream applications poses significant privacy risks. Several popular community platforms now offer convenient distribution of a large variety of pre-trained models. We introduce a novel poisoning technique that uses model-unlearning as an attack tool.
  arXiv  Detail & Related papers  (2024-08-30T15:35:09Z)
• Privacy Backdoors: Stealing Data with Corrupted Pretrained Models [23.54726973460633]
  Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. We show how to build privacy backdoors for a variety of models, including transformers.
  arXiv  Detail & Related papers  (2024-03-30T20:43:53Z)
• 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)
• SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models [74.58014281829946]
  We analyze the effectiveness of several representative attacks/defenses, including model stealing attacks, membership inference attacks, and backdoor detection on public models. Our evaluation empirically shows the performance of these attacks/defenses can vary significantly on public models compared to self-trained models.
  arXiv  Detail & Related papers  (2023-10-19T11:49:22Z)
• 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)
• Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples [67.66153875643964]
  Backdoor attacks are serious security threats to machine learning models. In this paper, we explore the task of purifying a backdoored model using a small clean dataset. By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk.
  arXiv  Detail & Related papers  (2023-07-20T03:56:04Z)
• CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning [77.27443885999404]
  Federated Learning (FL) is a setting for training machine learning models in distributed environments. We propose a novel method, CANIFE, that uses carefully crafted samples by a strong adversary to evaluate the empirical privacy of a training round.
  arXiv  Detail & Related papers  (2022-10-06T13:30:16Z)
• 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)
• 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.