PFGuard: A Generative Framework with Privacy and Fairness Safeguards

• URL: http://arxiv.org/abs/2410.02246v1
• Date: Thu, 3 Oct 2024 06:37:16 GMT
• Title: PFGuard: A Generative Framework with Privacy and Fairness Safeguards
• Authors: Soyeon Kim, Yuji Roh, Geon Heo, Steven Euijong Whang,
• Abstract summary: PFGuard is a generative framework with privacy and fairness safeguards. It balances privacy-fairness conflicts between fair and private training stages. Experiments show that PFGuard successfully generates synthetic data on high-dimensional data.
• Score: 14.504462873398461
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine existing privacy and fairness techniques to achieve both goals. However, naively combining these techniques can be insufficient due to privacy-fairness conflicts, where a sample in a minority group may be amplified for fairness, only to be suppressed for privacy. We demonstrate how these conflicts lead to adverse effects, such as privacy violations and unexpected fairness-utility tradeoffs. To mitigate these risks, we propose PFGuard, a generative framework with privacy and fairness safeguards, which simultaneously addresses privacy, fairness, and utility. By using an ensemble of multiple teacher models, PFGuard balances privacy-fairness conflicts between fair and private training stages and achieves high utility based on ensemble learning. Extensive experiments show that PFGuard successfully generates synthetic data on high-dimensional data while providing both fairness convergence and strict DP guarantees - the first of its kind to our knowledge.

Related papers

• Convergent Differential Privacy Analysis for General Federated Learning: the $f$-DP Perspective [57.35402286842029]
  Federated learning (FL) is an efficient collaborative training paradigm with a focus on local privacy. differential privacy (DP) is a classical approach to capture and ensure the reliability of private protections.
  arXiv  Detail & Related papers  (2024-08-28T08:22:21Z)
• Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives [48.48294460952039]
  This survey offers comprehensive descriptions of the privacy, security, and fairness issues in federated learning. We contend that there exists a trade-off between privacy and fairness and between security and sharing.
  arXiv  Detail & Related papers  (2024-06-16T10:31:45Z)
• Fairness and Privacy Guarantees in Federated Contextual Bandits [8.071147275221973]
  We model the algorithm's effectiveness using fairness regret. We show that both Fed-FairX-LinUCB and Priv-FairX-LinUCB achieve near-optimal fairness regret.
  arXiv  Detail & Related papers  (2024-02-05T21:38:23Z)
• Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning [10.473137837891162]
  Federated Learning (FL) is a novel privacy-protection distributed machine learning paradigm. We propose a privacy-protection fairness FL method to protect the privacy of the client model. We conclude the relationship between privacy, fairness and utility, and there is a tradeoff between these.
  arXiv  Detail & Related papers  (2023-11-30T02:19:35Z)
• Privacy and Fairness in Federated Learning: on the Perspective of Trade-off [58.204074436129716]
  Federated learning (FL) has been a hot topic in recent years. As two crucial ethical notions, the interactions between privacy and fairness are comparatively less studied.
  arXiv  Detail & Related papers  (2023-06-25T04:38:19Z)
• No free lunch theorem for security and utility in federated learning [20.481170500480395]
  In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. This article illustrates a general framework that formulates the trade-off between privacy loss and utility loss from a unified information-theoretic point of view.
  arXiv  Detail & Related papers  (2022-03-11T09:48:29Z)
• 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)
• Privacy Amplification via Shuffling for Linear Contextual Bandits [51.94904361874446]
  We study the contextual linear bandit problem with differential privacy (DP) We show that it is possible to achieve a privacy/utility trade-off between JDP and LDP by leveraging the shuffle model of privacy. Our result shows that it is possible to obtain a tradeoff between JDP and LDP by leveraging the shuffle model while preserving local privacy.
  arXiv  Detail & Related papers  (2021-12-11T15:23:28Z)
• A Privacy-Preserving and Trustable Multi-agent Learning Framework [34.28936739262812]
  This paper presents Privacy-preserving and trustable Distributed Learning (PT-DL) PT-DL is a fully decentralized framework that relies on Differential Privacy to guarantee strong privacy protections of the agents' data. The paper shows that PT-DL is resilient up to a 50% collusion attack, with high probability, in a malicious trust model.
  arXiv  Detail & Related papers  (2021-06-02T15:46:27Z)
• Federated $f$-Differential Privacy [19.499120576896228]
  Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information. We introduce federated $f$-differential privacy, a new notion specifically tailored to the federated setting. We then propose a generic private federated learning framework PriFedSync that accommodates a large family of state-of-the-art FL algorithms.
  arXiv  Detail & Related papers  (2021-02-22T16:28:21Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)

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.