Convolutional Neural Network Compression Based on Improved Fractal Decomposition Algorithm for Large Scale Optimization
Loading...
Date
2023
Authors
Llanza, Arcadi
Keddous, Fekhr Eddine
Shvai, Nadiya
Nakib, Amir
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Deep learning based methods have become the de-facto standard for various computer vision tasks. Nevertheless, they have repeatedly shown their vulnerability to various form of input perturbations such as pixels modification, region anonymization, etc. which are closely related to the adversarial attacks. This research particularly addresses the case of image anonymization, which is significantly important to preserve privacy and hence to secure digitized form of personal information from being exposed and potentially misused by different services that have captured it for various purposes. However, applying anonymization causes the classifier to provide different class decisions before and after applying it and therefore reduces the classifier’s reliability and usability. In order to achieve a robust solution to this problem we propose a novel anonymization procedure that allows the existing classifiers to become class decision invariant on the anonymized images without any modification requires to apply on the classification models. We conduct numerous experiments on the popular ImageNet benchmark as well as on a large scale industrial toll classification problem’s dataset. Obtained results confirm the efficiency and effectiveness of the proposed method as it obtained 0% rate of class decision change for both datasets compared to 15.95% on ImageNet and 0.18% on toll dataset obtained by applying the na¨ıve anonymization approaches. Moreover, it has shown a great potential to be applied to similar problems from different domains.
Description
Keywords
image anonymization, personal information, anonymized images, deep learning models, conference materials
Citation
Convolutional Neural Network Compression Based on Improved Fractal Decomposition Algorithm for Large Scale Optimization / Arcadi Llanza, Fekhr Eddine Keddous, Nadiya Shvai, Amir Nakib // IEEE International Conference on Systems, Man, and Cybernetics (SMC), Honolulu, Oahu, HI, USA. - 2023. - P. 5084-5089. - https://doi.org/10.1109/SMC53992.2023.10394477