In this section

Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks

Ayaz, F. , Zakariyya, I., Cano Reyes, J. , Keoh, S. L. , Singer, J. , Pau, D. and Mounia, K.-H. (2023) Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks. In: International Joint Conference on Neural Networks (IJCNN 2023), Gold Coast, Australia, 18-23 June 2023, (Accepted for Publication)

[img] Text
299217.pdf - Accepted Version
Restricted to Repository staff only
596kB

Item Type:Conference Proceedings
Additional Information:This work has been supported by the PETRAS National Centre of Excellence for IoT Systems Cybersecurity, funded by the UK EPSRC under grant number EP/S035362/1.
Keywords:Deep Neural Networks (DNNs), QKeras, Jacobian Regularization (JR), Adversarial Attacks
Status:Accepted for Publication
Refereed:Yes
Glasgow Author(s) Enlighten ID:Zakariyya, Mr Idris and Singer, Dr Jeremy and Cano Reyes, Dr Jose and Keoh, Dr Sye Loong and Ayaz, Ms Ferheen
Authors: Ayaz, F., Zakariyya, I., Cano Reyes, J., Keoh, S. L., Singer, J., Pau, D., and Mounia, K.-H.
College/School:College of Science and Engineering > School of Computing Science
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record

Funder and Project Information
Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
313487Multimodal AI-based Security at the EdgeJose Cano ReyesEngineering and Physical Sciences Research Council (EPSRC)5676863Computing Science
Deposit and Record Details