Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation

• URL: http://arxiv.org/abs/2409.02404v1
• Date: Wed, 4 Sep 2024 03:06:13 GMT
• Title: Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
• Authors: Shiming Ge, Bochao Liu, Pengju Wang, Yong Li, Dan Zeng,
• Abstract summary: Deep models may pose a privacy leakage risk in practical deployment. We propose a discriminative-generative distillation approach to learn privacy-preserving deep models. Our approach can control query cost over private data and accuracy degradation in a unified manner.
• Score: 24.868697898254368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and strong privacy. In this work, we propose a discriminative-generative distillation approach to learn privacy-preserving deep models. Our key idea is taking models as bridge to distill knowledge from private data and then transfer it to learn a student network via two streams. First, discriminative stream trains a baseline classifier on private data and an ensemble of teachers on multiple disjoint private subsets, respectively. Then, generative stream takes the classifier as a fixed discriminator and trains a generator in a data-free manner. After that, the generator is used to generate massive synthetic data which are further applied to train a variational autoencoder (VAE). Among these synthetic data, a few of them are fed into the teacher ensemble to query labels via differentially private aggregation, while most of them are embedded to the trained VAE for reconstructing synthetic data. Finally, a semi-supervised student learning is performed to simultaneously handle two tasks: knowledge transfer from the teachers with distillation on few privately labeled synthetic data, and knowledge enhancement with tangent-normal adversarial regularization on many triples of reconstructed synthetic data. In this way, our approach can control query cost over private data and mitigate accuracy degradation in a unified manner, leading to a privacy-preserving student model. Extensive experiments and analysis clearly show the effectiveness of the proposed approach.

Related papers

• Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation [35.37005050907983]
  We present an effective teacher-student learning approach to train privacy-preserving deep learning models. Massive synthetic data can be generated for model training without exposing data privacy. A student is trained on the synthetic data with the supervision of private labels.
  arXiv  Detail & Related papers  (2024-09-19T01:00:18Z)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
  Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners. FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
  arXiv  Detail & Related papers  (2024-03-10T08:41:22Z)
• Federated Learning Empowered by Generative Content [55.576885852501775]
  Federated learning (FL) enables leveraging distributed private data for model training in a privacy-preserving way. We propose a novel FL framework termed FedGC, designed to mitigate data heterogeneity issues by diversifying private data with generative content. We conduct a systematic empirical study on FedGC, covering diverse baselines, datasets, scenarios, and modalities.
  arXiv  Detail & Related papers  (2023-12-10T07:38:56Z)
• Distribution Shift Matters for Knowledge Distillation with Webly Collected Images [91.66661969598755]
  We propose a novel method dubbed Knowledge Distillation between Different Distributions" (KD$3$) We first dynamically select useful training instances from the webly collected data according to the combined predictions of teacher network and student network. We also build a new contrastive learning block called MixDistribution to generate perturbed data with a new distribution for instance alignment.
  arXiv  Detail & Related papers  (2023-07-21T10:08:58Z)
• Approximate, Adapt, Anonymize (3A): a Framework for Privacy Preserving Training Data Release for Machine Learning [3.29354893777827]
  We introduce a data release framework, 3A (Approximate, Adapt, Anonymize), to maximize data utility for machine learning. We present experimental evidence showing minimal discrepancy between performance metrics of models trained on real versus privatized datasets.
  arXiv  Detail & Related papers  (2023-07-04T18:37:11Z)
• Differentially Private Synthetic Data Generation via Lipschitz-Regularised Variational Autoencoders [3.7463972693041274]
  It is often overlooked that generative models are prone to memorising many details of individual training records. In this paper we explore an alternative approach for privately generating data that makes direct use of the inherentity in generative models.
  arXiv  Detail & Related papers  (2023-04-22T07:24:56Z)
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification [101.1886788396803]
  Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models. In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
  arXiv  Detail & Related papers  (2021-09-12T15:51:41Z)
• Dual Discriminator Adversarial Distillation for Data-free Model Compression [36.49964835173507]
  We propose Dual Discriminator Adversarial Distillation (DDAD) to distill a neural network without any training data or meta-data. To be specific, we use a generator to create samples through dual discriminator adversarial distillation, which mimics the original training data. The proposed method obtains an efficient student network which closely approximates its teacher network, despite using no original training data.
  arXiv  Detail & Related papers  (2021-04-12T12:01:45Z)
• Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information [55.866673486753115]
  We propose an extendable and elastic learning framework to preserve privacy and security. The proposed framework is named distributed Asynchronized Discriminator Generative Adrial Networks (AsynDGAN)
  arXiv  Detail & Related papers  (2020-12-15T20:41:24Z)
• GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators [74.16405337436213]
  We propose Gradient-sanitized Wasserstein Generative Adrial Networks (GS-WGAN) GS-WGAN allows releasing a sanitized form of sensitive data with rigorous privacy guarantees. We find our approach consistently outperforms state-of-the-art approaches across multiple metrics.
  arXiv  Detail & Related papers  (2020-06-15T10:01:01Z)
• Data-Free Network Quantization With Adversarial Knowledge Distillation [39.92282726292386]
  In this paper, we consider data-free network quantization with synthetic data. The synthetic data are generated from a generator, while no data are used in training the generator and in quantization. We show the gain of producing diverse adversarial samples by using multiple generators and multiple students.
  arXiv  Detail & Related papers  (2020-05-08T16:24:55Z)

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.