Bounding Training Data Reconstruction in DP-SGD

• URL: http://arxiv.org/abs/2302.07225v3
• Date: Mon, 30 Oct 2023 10:12:11 GMT
• Title: Bounding Training Data Reconstruction in DP-SGD
• Authors: Jamie Hayes, Saeed Mahloujifar, Borja Balle
• Abstract summary: Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other threats like reconstruction attacks attempting to extract complete training examples. Recent works provide evidence that if one does not need to protect against membership attacks but instead only wants to protect against training data reconstruction, then utility of private models can be improved.
• Score: 42.36933026300976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differentially private training offers a protection which is usually interpreted as a guarantee against membership inference attacks. By proxy, this guarantee extends to other threats like reconstruction attacks attempting to extract complete training examples. Recent works provide evidence that if one does not need to protect against membership attacks but instead only wants to protect against training data reconstruction, then utility of private models can be improved because less noise is required to protect against these more ambitious attacks. We investigate this further in the context of DP-SGD, a standard algorithm for private deep learning, and provide an upper bound on the success of any reconstruction attack against DP-SGD together with an attack that empirically matches the predictions of our bound. Together, these two results open the door to fine-grained investigations on how to set the privacy parameters of DP-SGD in practice to protect against reconstruction attacks. Finally, we use our methods to demonstrate that different settings of the DP-SGD parameters leading to the same DP guarantees can result in significantly different success rates for reconstruction, indicating that the DP guarantee alone might not be a good proxy for controlling the protection against reconstruction attacks.

Related papers

• Bayes' capacity as a measure for reconstruction attacks in federated learning [10.466570297146953]
  We formalise the reconstruction threat model using the information-theoretic framework of quantitative information flow. We show that the Bayes' capacity, related to the Sibson mutual information of order infinity, represents a tight upper bound on the leakage of the DP-SGD algorithm to an adversary.
  arXiv  Detail & Related papers  (2024-06-19T13:58:42Z)
• Visual Privacy Auditing with Diffusion Models [52.866433097406656]
  We propose a reconstruction attack based on diffusion models (DMs) that assumes adversary access to real-world image priors. We show that (1) real-world data priors significantly influence reconstruction success, (2) current reconstruction bounds do not model the risk posed by data priors well, and (3) DMs can serve as effective auditing tools for visualizing privacy leakage.
  arXiv  Detail & Related papers  (2024-03-12T12:18:55Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• Does Differential Privacy Prevent Backdoor Attacks in Practice? [8.951356689083166]
  We investigate the effectiveness of Differential Privacy techniques in preventing backdoor attacks in machine learning models. We propose Label-DP as a faster and more accurate alternative to DP-SGD and PATE.
  arXiv  Detail & Related papers  (2023-11-10T18:32:08Z)
• 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)
• Bounding Training Data Reconstruction in Private (Deep) Learning [40.86813581191581]
  Differential privacy is widely accepted as the de facto method for preventing data leakage in ML. Existing semantic guarantees for DP focus on membership inference. We show that two distinct privacy accounting methods -- Renyi differential privacy and Fisher information leakage -- both offer strong semantic protection against data reconstruction attacks.
  arXiv  Detail & Related papers  (2022-01-28T19:24:30Z)
• DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations [54.960853673256]
  We show that strong data augmentations, such as mixup and random additive noise, nullify poison attacks while enduring only a small accuracy trade-off. A rigorous analysis of DP-InstaHide shows that mixup does indeed have privacy advantages, and that training with k-way mixup provably yields at least k times stronger DP guarantees than a naive DP mechanism.
  arXiv  Detail & Related papers  (2021-03-02T23:07:31Z)
• Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses [59.58128343334556]
  We introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adversarial training. We propose Guided Adversarial Margin Attack (GAMA), which utilizes function mapping of the clean image to guide the generation of adversaries. We also propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses.
  arXiv  Detail & Related papers  (2020-11-30T16:39:39Z)

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.