Network Inversion for Training-Like Data Reconstruction

• URL: http://arxiv.org/abs/2410.16884v1
• Date: Tue, 22 Oct 2024 10:42:08 GMT
• Title: Network Inversion for Training-Like Data Reconstruction
• Authors: Pirzada Suhail, Amit Sethi,
• Abstract summary: We present Training-Like Data Reconstruction (TLDR), a network inversion-based approach to reconstruct training-like data from trained models. To validate our approach, we conduct empirical evaluations on multiple standard vision classification datasets.
• Score: 3.004632712148892
• License:
• Abstract: Machine Learning models are often trained on proprietary and private data that cannot be shared, though the trained models themselves are distributed openly assuming that sharing model weights is privacy preserving, as training data is not expected to be inferred from the model weights. In this paper, we present Training-Like Data Reconstruction (TLDR), a network inversion-based approach to reconstruct training-like data from trained models. To begin with, we introduce a comprehensive network inversion technique that learns the input space corresponding to different classes in the classifier using a single conditioned generator. While inversion may typically return random and arbitrary input images for a given output label, we modify the inversion process to incentivize the generator to reconstruct training-like data by exploiting key properties of the classifier with respect to the training data along with some prior knowledge about the images. To validate our approach, we conduct empirical evaluations on multiple standard vision classification datasets, thereby highlighting the potential privacy risks involved in sharing machine learning models.

Related papers

• Comparison of self-supervised in-domain and supervised out-domain transfer learning for bird species recognition [0.19183348587701113]
  Transferring the weights of a pre-trained model to assist another task has become a crucial part of modern deep learning. Our experiments will demonstrate the usefulness of in-domain models and datasets for bird species recognition.
  arXiv  Detail & Related papers  (2024-04-26T08:47:28Z)
• Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model [32.094290282897894]
  Federated learning aims to train a collective model from physically isolated clients while safeguarding the privacy of users' data. We propose a novel lightweight unsupervised federated learning approach that leverages unlabeled data on each client to perform lightweight model training and communication. Our proposed method greatly enhances model performance in comparison to CLIP's zero-shot predictions and even outperforms supervised federated learning benchmark methods.
  arXiv  Detail & Related papers  (2024-04-17T03:42:48Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Privacy Side Channels in Machine Learning Systems [87.53240071195168]
  We introduce privacy side channels: attacks that exploit system-level components to extract private information. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. We further show that systems which block language models from regenerating training data can be exploited to exfiltrate private keys contained in the training set.
  arXiv  Detail & Related papers  (2023-09-11T16:49:05Z)
• Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings [57.45332961252628]
  Privacy-preserving machine learning in data-sharing processes is an ever-critical task. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data.
  arXiv  Detail & Related papers  (2022-11-10T17:36:58Z)
• Certified Robustness in Federated Learning [54.03574895808258]
  We study the interplay between federated training, personalization, and certified robustness. We find that the simple federated averaging technique is effective in building not only more accurate, but also more certifiably-robust models.
  arXiv  Detail & Related papers  (2022-06-06T12:10:53Z)
• Reconstructing Training Data with Informed Adversaries [30.138217209991826]
  Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. We show it is feasible to reconstruct the remaining data point in this stringent threat model.
  arXiv  Detail & Related papers  (2022-01-13T09:19:25Z)
• Reconstructing Training Data from Diverse ML Models by Ensemble Inversion [8.414622657659168]
  Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model, has attracted increasing research attention. We propose an ensemble inversion technique that estimates the distribution of original training data by training a generator constrained by an ensemble of trained models. We achieve high quality results without any dataset and show how utilizing an auxiliary dataset that's similar to the presumed training data improves the results.
  arXiv  Detail & Related papers  (2021-11-05T18:59:01Z)
• Decentralized Federated Learning Preserves Model and Data Privacy [77.454688257702]
  We propose a fully decentralized approach, which allows to share knowledge between trained models. Students are trained on the output of their teachers via synthetically generated input data. The results show that an untrained student model, trained on the teachers output reaches comparable F1-scores as the teacher.
  arXiv  Detail & Related papers  (2021-02-01T14:38:54Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)

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.