Investigating Privacy Attacks in the Gray-Box Setting to Enhance Collaborative Learning Schemes

• URL: http://arxiv.org/abs/2409.17283v1
• Date: Wed, 25 Sep 2024 18:49:21 GMT
• Title: Investigating Privacy Attacks in the Gray-Box Setting to Enhance Collaborative Learning Schemes
• Authors: Federico Mazzone, Ahmad Al Badawi, Yuriy Polyakov, Maarten Everts, Florian Hahn, Andreas Peter,
• Abstract summary: We study privacy attacks in the gray-box setting, where the attacker has only limited access to the model. We deploy SmartNNCrypt, a framework that tailors homomorphic encryption to protect the portions of the model posing higher privacy risks.
• Score: 7.651569149118461
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries to extract information about a model's training dataset by exploiting access to model parameters during or after training. In this work, we study privacy attacks in the gray-box setting, where the attacker has only limited access - in terms of view and actions - to the model. The findings of our investigation provide new insights for the development of privacy-preserving collaborative learning solutions. We deploy SmartCryptNN, a framework that tailors homomorphic encryption to protect the portions of the model posing higher privacy risks. Our solution offers a trade-off between privacy and efficiency, which varies based on the extent and selection of the model components we choose to protect. We explore it on dense neural networks, where through extensive evaluation of diverse datasets and architectures, we uncover instances where a favorable sweet spot in the trade-off can be achieved by safeguarding only a single layer of the network. In one of such instances, our approach trains ~4 times faster compared to fully encrypted solutions, while reducing membership leakage by 17.8 times compared to plaintext solutions.

Related papers

• Model Inversion Attacks: A Survey of Approaches and Countermeasures [59.986922963781]
  Recently, a new type of privacy attack, the model inversion attacks (MIAs), aims to extract sensitive features of private data for training. Despite the significance, there is a lack of systematic studies that provide a comprehensive overview and deeper insights into MIAs. This survey aims to summarize up-to-date MIA methods in both attacks and defenses.
  arXiv  Detail & Related papers  (2024-11-15T08:09:28Z)
• Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning [54.30994558765057]
  The study pioneers a comprehensive privacy protection framework that safeguards image data privacy concurrently during data sharing and model publication. We propose an interactive image privacy protection framework that utilizes generative machine learning models to modify image information at the attribute level. Within this framework, we instantiate two modules: a differential privacy diffusion model for protecting attribute information in images and a feature unlearning algorithm for efficient updates of the trained model on the revised image dataset.
  arXiv  Detail & Related papers  (2024-09-05T07:55:55Z)
• 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)
• 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)
• A Unified View of Differentially Private Deep Generative Modeling [60.72161965018005]
  Data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released.
  arXiv  Detail & Related papers  (2023-09-27T14:38:16Z)
• Privacy-Preserving Wavelet Wavelet Neural Network with Fully Homomorphic Encryption [5.010425616264462]
  Privacy-Preserving Machine Learning (PPML) aims to protect the privacy and provide security to the data used in building Machine Learning models. We propose a fully homomorphic encrypted wavelet neural network to protect privacy and at the same time not compromise on the efficiency of the model.
  arXiv  Detail & Related papers  (2022-05-26T10:40:31Z)
• Federated Deep Learning with Bayesian Privacy [28.99404058773532]
  Federated learning (FL) aims to protect data privacy by cooperatively learning a model without sharing private data among users. Homomorphic encryption (HE) based methods provide secure privacy protections but suffer from extremely high computational and communication overheads. Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity.
  arXiv  Detail & Related papers  (2021-09-27T12:48:40Z)
• Robustness Threats of Differential Privacy [70.818129585404]
  We experimentally demonstrate that networks, trained with differential privacy, in some settings might be even more vulnerable in comparison to non-private versions. We study how the main ingredients of differentially private neural networks training, such as gradient clipping and noise addition, affect the robustness of the model.
  arXiv  Detail & Related papers  (2020-12-14T18:59:24Z)
• Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries [74.59376038272661]
  We introduce sampling attack, a novel membership inference technique that unlike other standard membership adversaries is able to work under severe restriction of no access to scores of the victim model. We show that a victim model that only publishes the labels is still susceptible to sampling attacks and the adversary can recover up to 100% of its performance. For defense, we choose differential privacy in the form of gradient perturbation during the training of the victim model as well as output perturbation at prediction time.
  arXiv  Detail & Related papers  (2020-09-01T12:54:54Z)
• SPEED: Secure, PrivatE, and Efficient Deep learning [2.283665431721732]
  We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-16T19:31:52Z)

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.