Title | Improving Security of Neural Networks in the Identification Module of Decision Support Systems |
Publication Type | Conference Paper |
Year of Publication | 2020 |
Authors | Monakhov, Yuri, Monakhov, Mikhail, Telny, Andrey, Mazurok, Dmitry, Kuznetsova, Anna |
Conference Name | 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) |
Keywords | adversarial attacks, Artificial neural networks, cyber physical systems, Cyber-physical systems, Decision Support System, Metrics, Neural Network Security, Neural networks, policy-based governance, pubcrawl, Resiliency |
Abstract | In recent years, neural networks have been implemented while solving various tasks. Deep learning algorithms provide state of the art performance in computer vision, NLP, speech recognition, speaker recognition and many other fields. In spite of the good performance, neural networks have significant drawback- they have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. While being imperceptible to a human eye, such perturbations lead to significant drop in classification accuracy. It is demonstrated by many studies related to neural network security. Considering the pros and cons of neural networks, as well as a variety of their applications, developing of the methods to improve the robustness of neural networks against adversarial attacks becomes an urgent task. In the article authors propose the “minimalistic” attacker model of the decision support system identification unit, adaptive recommendations on security enhancing, and a set of protective methods. Suggested methods allow for significant increase in classification accuracy under adversarial attacks, as it is demonstrated by an experiment outlined in this article. |
DOI | 10.1109/USBEREIT48449.2020.9117651 |
Citation Key | monakhov_improving_2020 |