Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks

Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks

  • Post by:
  • August 17, 2021
  • Comments off

I. Siniosoglou, V. Argyriou, S. Bibi, T. Lagkas, P. Sarigiannidis: Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks. The 16th International Conference on Availability, Reliability and Security, 2021.

Abstract

While the technology of Deep Learning (DL) is a powerful tool when properly trained for image analysis and classification applications, some factors for its optimization rely solely on the training data and their environment. In an effort to tackle the problem of knowledge bias created during the training process of a Deep Neural Network (DNN) and specifically Adversarial Networks for image augmentation, this work presents an entirely unsupervised methodology for discovering the unfairness level of Deep Learning (DL) models and in extend, its wrongly accumulated or biased classes. Fdi, the proposed evaluation metric for quantizing the level of unfairness of a model is introduced, along with the method of weighting the model’s knowledge and producing its weakest aspects in a data-agnostic way.

BibTeX (Download)

@conference{Siniosoglou2021c,
title = {Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks},
author = {I. Siniosoglou and V. Argyriou and S. Bibi and T. Lagkas and P. Sarigiannidis},
doi = {10.1145/3465481.3470478},
year  = {2021},
date = {2021-08-17},
booktitle = {The 16th International Conference on Availability, Reliability and Security},
pages = {1-6},
abstract = {While the technology of Deep Learning (DL) is a powerful tool when properly trained for image analysis and classification applications, some factors for its optimization rely solely on the training data and their environment. In an effort to tackle the problem of knowledge bias created during the training process of a Deep Neural Network (DNN) and specifically Adversarial Networks for image augmentation, this work presents an entirely unsupervised methodology for discovering the unfairness level of Deep Learning (DL) models and in extend, its wrongly accumulated or biased classes. Fdi, the proposed evaluation metric for quantizing the level of unfairness of a model is introduced, along with the method of weighting the model’s knowledge and producing its weakest aspects in a data-agnostic way.},
keywords = {adverserial federated networks, machine learning, security},
pubstate = {published},
tppubtype = {conference}
}
Categories:
Skip to content