Affiliation:
1. Department of Electrical and Computer Engineering, University of Cyprus, 2109 Nicosia, Cyprus
Abstract
Nowadays, due to their excellent prediction capabilities, the use of artificial neural networks (ANNs) in software has significantly increased. One of the most important aspects of ANNs is robustness. Most existing studies on robustness focus on adversarial attacks and complete redundancy schemes in ANNs. Such redundancy methods for robustness are not easily applicable in modern embedded systems. This work presents a study, based on simulations, about the robustness of ANNs used for prediction purposes based on weight alterations. We devise a method to increase the robustness of ANNs directly from ANN characteristics. By using this method, only the most important neurons/connections are replicated, keeping the additional hardware overheads to a minimum. For implementation and evaluation purposes, the networks-on-chip (NoC) case, which is the next generation of system-on-chip, was used as a case study. The proposed study/method was validated using simulations and can be used for larger and different types of networks and hardware due to its scalable nature. The simulation results obtained using different PARSEC (Princeton Application Repository for Shared-Memory Computers) benchmark suite traffic show that a high level of robustness can be achieved with minimum hardware requirements in comparison to other works.
Subject
Computational Mathematics,Computational Theory and Mathematics,Numerical Analysis,Theoretical Computer Science
Reference22 articles.
1. A design space exploration framework for ANN-Based fault detection in hardware systems;Savva;J. Electr. Comput. Eng.,2017
2. Nakamura, R., Sekiya, Y., Miyamoto, D., Okada, K., and Ishihara, T. (2018). Malicious Host Detection by Imaging SYN Packets and a Neural Network, International Symposium on Networks, Computers and Communications (ISNCC).
3. Carlini, N., and Wagner, D. (2017, January 22–24). Towards evaluating the robustness of neural networks. Proceedings of the IEEE Symposium on Security and Privacy, San Jose, CA, USA.
4. A geometric perspective on the robustness of deep networks;Fawzi;IEEE Signal Process. Mag.,2017
5. Li, Y., Liu, Y., Li, M., Tian, Y., and Luo, B. (2019, January 9–13). D2NN: A fine-grained dual modular redundancy framework for deep neural networks. Proceedings of the ACSAC 35th Annual Computer Security Applications Conference, San Juan, PR, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献