Detection of Cyber Security Threats Using Iot Deep Learning

  • Kapil Wanaskar, Tanishq Kothari, Puneeth Kumar B S, Devananda S N, Sridhara S B , Atharav Hedage
Keywords: : IoT, cyber security, Deep Learning, IDS, QoS, etc.


The Internet of Things (IoT) is a ground-breaking innovation that connects both living and non-living objects in the globe. Because of this, there will be an increase in the number of cyber-attacks on IoT deployments. This makes it critical for each system to be completely safe, or else users may choose not to make use of the technology. Massive losses were caused by DDoS attacks that recently targeted many Internet of Things (IoT) networks. In this post, we've presented a unified approach for detecting stolen data from software and malware across the Internet of Things (IoT) network. The Tensor Flow deep neural system is suggested to classify stolen programming with source code literary theft. To disseminate raucous information while also increasing the importance of each token in relation to source code forgery, tokenization, and measuring. This technique is also used in source code to identify literary theft. Google Code Jam (GCJ) collects data to investigate the theft of utilisations. GCJ is run by Google. In addition, the deep neural system is used in the Internet of Things (IoT) network to detect vindictive contaminations via colour picture representation. The Maling dataset was used to gather the malware samples. In comparison to current approaches, the results indicate that the methodology being presented for assessing IoT cyber security threats has a better categorization efficiency.

How to Cite
Devananda S N, Sridhara S B , Atharav Hedage, K. W. T. K. P. K. B. S. (2021). Detection of Cyber Security Threats Using Iot Deep Learning. Design Engineering, 3493-3501. Retrieved from