• ISSN: 2349-6002
  • UGC Approved Journal No 47859

FOG-BASED ATTACK DETECTION FRAMEWORK FOR INTERNET OF THINGS USING DEEP Learning

  • Unique Paper ID: 159911
  • Volume: 9
  • Issue: 12
  • PageNo: 814-829
  • Abstract:
  • The number of cyber-attacks and data breaches has immensely increased across different enterprises, companies, and diligence as a result of the exploitation of the sins in securing Internet of Effects ( IoT) bias. The added number of biases connected to IoT and its different protocols has led to the growing volume of zero-day attacks. Deep literacy( DL) has demonstrated its superiority in big data fields and cyber-security. lately, DL has been used in cyber-attack discovery because of its capability of rooting and learning deep features of known attacks and detecting unknown attacks without the need for homemade point engineering. still, DL can not be enforced on IoT bias with limited coffers because it requires expansive calculation, strong power and storehouse capabilities. This paper presents a comprehensive attack discovery frame of a distributed, robust, and high discovery rate to descry several IoT cyber-attacks using DL. The proposed frame implements an attack sensor on fog bumps because of its distributed nature, high computational capacity and propinquity to edge bias. Six DL models are compared to identify the DL model with the stylish performance. All DL models are estimated using five different datasets, each of which involves colourful attacks. trials show that the long short-term memory model outperforms the five other DL models. The proposed frame is effective in terms of response time and discovery delicacy and can descry several types of cyber-attacks with99.97 discovery rate and99.96 discovery delicacy in double bracket and99.65 discovery delicacy in multi-class bracket.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 9
  • Issue: 12
  • PageNo: 814-829

FOG-BASED ATTACK DETECTION FRAMEWORK FOR INTERNET OF THINGS USING DEEP Learning

Related Articles