Sharing Models or Coresets: A Study based on Membership Inference Attack

• URL: http://arxiv.org/abs/2007.02977v1
• Date: Mon, 6 Jul 2020 18:06:53 GMT
• Title: Sharing Models or Coresets: A Study based on Membership Inference Attack
• Authors: Hanlin Lu, Changchang Liu, Ting He, Shiqiang Wang and Kevin S. Chan
• Abstract summary: Distributed machine learning aims at training a global model based on distributed data without collecting all the data to a centralized location. Two approaches have been proposed: collecting and aggregating local models (federated learning) and collecting and training over representative data summaries (coreset) Our experiments quantify the accuracy-privacy-cost tradeoff of each approach, and reveal a nontrivial comparison that can be used to guide the design of model training processes.
• Score: 17.562474629669513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different approaches have been proposed: collecting and aggregating local models (federated learning) and collecting and training over representative data summaries (coreset). While each approach preserves data privacy to some extent thanks to not sharing the raw data, the exact extent of protection is unclear under sophisticated attacks that try to infer the raw data from the shared information. We present the first comparison between the two approaches in terms of target model accuracy, communication cost, and data privacy, where the last is measured by the accuracy of a state-of-the-art attack strategy called the membership inference attack. Our experiments quantify the accuracy-privacy-cost tradeoff of each approach, and reveal a nontrivial comparison that can be used to guide the design of model training processes.

Related papers

• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains [9.429772474335122]
  We focus on scenarios where data distributions vary across multiple segments of the entire population. We propose a two-stage multiply robust estimation method to improve model performance on each individual segment. Our method is designed to be implemented with commonly used off-the-shelf machine learning models.
  arXiv  Detail & Related papers  (2024-02-21T22:01:10Z)
• Universal Semi-supervised Model Adaptation via Collaborative Consistency Training [92.52892510093037]
  We introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA) We propose a collaborative consistency training framework that regularizes the prediction consistency between two models. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
  arXiv  Detail & Related papers  (2023-07-07T08:19:40Z)
• Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus [11.414398732656839]
  We propose a framework that embeds differential privacy into decentralized deep learning and secures each agent's local dataset during and after cooperative training. We prove convergence guarantees for algorithms derived from this framework and demonstrate its practical utility when applied to subgradient and ADMM decentralized approaches.
  arXiv  Detail & Related papers  (2023-06-24T07:46:00Z)
• Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers [71.70205894168039]
  We consider instance-wise unlearning, of which the goal is to delete information on a set of instances from a pre-trained model. We propose two methods that reduce forgetting on the remaining data: 1) utilizing adversarial examples to overcome forgetting at the representation-level and 2) leveraging weight importance metrics to pinpoint network parameters guilty of propagating unwanted information.
  arXiv  Detail & Related papers  (2023-01-27T07:53:50Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets [53.866927712193416]
  We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak private details belonging to other parties. Our attacks are effective across membership inference, attribute inference, and data extraction. Our results cast doubts on the relevance of cryptographic privacy guarantees in multiparty protocols for machine learning.
  arXiv  Detail & Related papers  (2022-03-31T18:06:28Z)
• Enhanced Membership Inference Attacks against Machine Learning Models [9.26208227402571]
  Membership inference attacks are used to quantify the private information that a model leaks about the individual data points in its training set. We derive new attack algorithms that can achieve a high AUC score while also highlighting the different factors that affect their performance. Our algorithms capture a very precise approximation of privacy loss in models, and can be used as a tool to perform an accurate and informed estimation of privacy risk in machine learning models.
  arXiv  Detail & Related papers  (2021-11-18T13:31:22Z)
• Privacy-Preserving Federated Learning on Partitioned Attributes [6.661716208346423]
  Federated learning empowers collaborative training without exposing local data or models. We introduce an adversarial learning based procedure which tunes a local model to release privacy-preserving intermediate representations. To alleviate the accuracy decline, we propose a defense method based on the forward-backward splitting algorithm.
  arXiv  Detail & Related papers  (2021-04-29T14:49:14Z)
• Delving into Data: Effectively Substitute Training for Black-box Attack [84.85798059317963]
  We propose a novel perspective substitute training that focuses on designing the distribution of data used in the knowledge stealing process. The combination of these two modules can further boost the consistency of the substitute model and target model, which greatly improves the effectiveness of adversarial attack.
  arXiv  Detail & Related papers  (2021-04-26T07:26:29Z)
• Federating Recommendations Using Differentially Private Prototypes [16.29544153550663]
  We propose a new federated approach to learning global and local private models for recommendation without collecting raw data. By requiring only two rounds of communication, we both reduce the communication costs and avoid the excessive privacy loss. We show local adaptation of the global model allows our method to outperform centralized matrix-factorization-based recommender system models.
  arXiv  Detail & Related papers  (2020-03-01T22:21:31Z)

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.