Knowledge Cross-Distillation for Membership Privacy

• URL: http://arxiv.org/abs/2111.01363v1
• Date: Tue, 2 Nov 2021 04:16:08 GMT
• Title: Knowledge Cross-Distillation for Membership Privacy
• Authors: Rishav Chourasia, Batnyam Enkhtaivan, Kunihiro Ito, Junki Mori, Isamu Teranishi, Hikaru Tsuchida
• Abstract summary: A membership inference attack (MIA) poses privacy risks on the training data of a machine learning model. We propose a novel defense against MIAs using knowledge distillation without requiring public data.
• Score: 0.9087641068861045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A membership inference attack (MIA) poses privacy risks on the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs, distillation for membership privacy (DMP), requires not only private data to protect but a large amount of unlabeled public data. However, in certain privacy-sensitive domains, such as medical and financial, the availability of public data is not obvious. Moreover, a trivial method to generate the public data by using generative adversarial networks significantly decreases the model accuracy, as reported by the authors of DMP. To overcome this problem, we propose a novel defense against MIAs using knowledge distillation without requiring public data. Our experiments show that the privacy protection and accuracy of our defense are comparable with those of DMP for the benchmark tabular datasets used in MIA researches, Purchase100 and Texas100, and our defense has much better privacy-utility trade-off than those of the existing defenses without using public data for image dataset CIFAR10.

Related papers

• FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation [4.772368796656325]
  In practice, controlled data access remains a mainstream method for protecting data privacy in many industrial and research environments. We developed the demo prototype FT-PrivacyScore to show that it's possible to efficiently and quantitatively estimate the privacy risk of participating in a model fine-tuning task.
  arXiv  Detail & Related papers  (2024-10-30T02:41:26Z)
• A Zero Auxiliary Knowledge Membership Inference Attack on Aggregate Location Data [8.795538320219082]
  We develop the first Zero Auxiliary Knowledge (ZK) MIA on aggregate location data. This eliminates the need for an auxiliary dataset of real individual traces. We show that ZK MIA remains highly effective even when the adversary only knows a small fraction of their target's location history.
  arXiv  Detail & Related papers  (2024-06-26T18:14:36Z)
• $\alpha$-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing [4.475091558538915]
  This paper adopts Arimoto's $alpha$-Mutual Information as a tunable privacy measure. We formulate a general distortion-based mechanism that manipulates the original data to offer privacy protection.
  arXiv  Detail & Related papers  (2023-10-27T16:26:14Z)
• A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses [12.34501903200183]
  We propose a baseline defense that enables the utility-privacy tradeoff with respect to both training and reference data to be easily understood. Our experiments show that, surprisingly, it outperforms the most well-studied and current state-of-the-art empirical privacy defenses.
  arXiv  Detail & Related papers  (2023-10-18T17:07:07Z)
• Students Parrot Their Teachers: Membership Inference on Model Distillation [54.392069096234074]
  We study the privacy provided by knowledge distillation to both the teacher and student training sets. Our attacks are strongest when student and teacher sets are similar, or when the attacker can poison the teacher set.
  arXiv  Detail & Related papers  (2023-03-06T19:16:23Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)
• Certified Data Removal in Sum-Product Networks [78.27542864367821]
  Deleting the collected data is often insufficient to guarantee data privacy. UnlearnSPN is an algorithm that removes the influence of single data points from a trained sum-product network.
  arXiv  Detail & Related papers  (2022-10-04T08:22:37Z)
• No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy" [75.98836424725437]
  New methods designed to preserve data privacy require careful scrutiny. Failure to preserve privacy is hard to detect, and yet can lead to catastrophic results when a system implementing a privacy-preserving'' method is attacked.
  arXiv  Detail & Related papers  (2022-09-29T17:50:23Z)
• On the Privacy Effect of Data Enhancement via the Lens of Memorization [20.63044895680223]
  We propose to investigate privacy from a new perspective called memorization. Through the lens of memorization, we find that previously deployed MIAs produce misleading results as they are less likely to identify samples with higher privacy risks. We demonstrate that the generalization gap and privacy leakage are less correlated than those of the previous results.
  arXiv  Detail & Related papers  (2022-08-17T13:02:17Z)
• The Privacy Onion Effect: Memorization is Relative [76.46529413546725]
  We show an Onion Effect of memorization: removing the "layer" of outlier points that are most vulnerable exposes a new layer of previously-safe points to the same attack. It suggests that privacy-enhancing technologies such as machine unlearning could actually harm the privacy of other users.
  arXiv  Detail & Related papers  (2022-06-21T15:25:56Z)
• 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.