Hybrid CatBoost Regression model based Intrusion Detection System in IoT-Enabled Networks

• Main Authors: Latha, R, Bommi, R.M.
• Format: Conference Proceeding
• Language: English
• Subjects: Cyber-attacks; Feature extraction; Intrusion detection; Intrusion detection system; IoT attacks; Network security; Organizations; Safety; Sigma-delta modulation; smart city; Telecommunication traffic; Urban areas
• ISSN: 2693-3934
• DOI: 10.1109/ICEES57979.2023.10110148

To protect organization from random network attacks is highly important and that will save a massive information to be hacked in network traffic. The significant piece of framework utilized here to shield system from network dangers and guaranteeing elevated degree of safety. The huge measure of secret information, exchange information, exercises and subsequent meet-ups are transferred to the organization in current days through basic advances. Thus it is become adaptable for end clients to transfer the information securely over the cloud beyond intrusion attacks. Each time the client login to the specific organization empower the authorized person to access nodes, to acknowledge every access of the contributions for a specific timeframe is developed. The proposed system is focused on creating a robust model to detect network attacks coming as intrusion for IoT devices. The system develops a CatBoost regression model using IDS2017 dataset. The presented approach considers various attributes as key whole parameter for finding the presence of intrusion attacks over the network. The presented system achieved 92.5% of accuracy and compared with various states of art approaches.