Humans Don’t Get Fooled:Does Predictive Coding Defend Against Adversarial Attack?
Proceedings of the Canadian Conference on Artificial Intelligence · 27.05.2024
DOI: 10.21428/594757db.1a0d2332 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Canadian Conference on Artificial Intelligence, online erschienen am 27.05.2024. Verfasst von Junteng Zheng und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The success of backpropagation, a foundational method in machine learning, has somewhat overshadowed the potential of biologically plausible learning. However, a prevalent threat to contemporary artificial neural networks – trained with backpropagation – is their fragility to adversarial attack, in stark contrast to human visual perception. In our experiments, we demonstrate that predictive coding networks, a biologically plausible learning approach, exhibit robustness against adversarial attacks of various forms. This finding may provide a novel perspective on enhancing the robustness of machine learning models and demonstrating the potential of further applying biologically plausible learning methods.
Zitieren
APA
Zheng, J., & Orchard, J. (2024). Humans Don’t Get Fooled:Does Predictive Coding Defend Against Adversarial Attack?. Proceedings of the Canadian Conference on Artificial Intelligence. https://doi.org/10.21428/594757db.1a0d2332
Vancouver
Zheng J, Orchard J. Humans Don’t Get Fooled:Does Predictive Coding Defend Against Adversarial Attack?. Proceedings of the Canadian Conference on Artificial Intelligence. 2024. doi:10.21428/594757db.1a0d2332
BibTeX
@article{Zheng2024,
author = {Zheng, Junteng and Orchard, Jeff},
title = {Humans Don’t Get Fooled:Does Predictive Coding Defend Against Adversarial Attack?},
journal = {Proceedings of the Canadian Conference on Artificial Intelligence},
year = {2024},
doi = {10.21428/594757db.1a0d2332}
}
EUVIMED