Unsupervised Ethical Equity Evaluation of Adversarial Federated Networks
Authors:
Open Access
- 17 August 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 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
Funding Information
- Horizon 2020 Framework Programme (957406)
This publication has 18 references indexed in Scilit:
- Federated Learning: Challenges, Methods, and Future DirectionsIEEE Signal Processing Magazine, 2020
- Data Augmentation for Discrimination Prevention and Bias Disambiguation2020
- A modular CNN-based building detector for remote sensing imagesComputer Networks, 2020
- Fairness GAN: Generating datasets with fairness properties using a generative adversarial networkIBM Journal of Research and Development, 2019
- Crowd behavior analysis from fixed and moving cameras2019
- Quality Management of Surveillance Multimedia Streams Via Federated SDN Controllers in Fiwi-Iot Integrated Deployment EnvironmentsIEEE Access, 2018
- Modeling the Internet of Things Under Attack: A G-network ApproachIEEE Internet of Things Journal, 2017
- VisIoT: A threat visualisation tool for IoT systems security2015
- Photometric stereo with an arbitrary number of illuminantsComputer Vision and Image Understanding, 2010
- Chapter 1 Photometric Stereo: An Overview2009