Intrusion detection system using autoencoder based deep neural network for SME cybersecurity

• Main Authors: Khaizuran Aqhar, Ubaidillah, Syifak Izhar, Hisham, Ferda, Ernawan, Badshah, Gran, Suharto, Edy
• Format: Conference or Workshop Item
• Language: English; English
• Published: Institute of Electrical and Electronics Engineers Inc. 2021
• Subjects: QA75 Electronic computers. Computer science; QA76 Computer software; T Technology (General); TA Engineering (General). Civil engineering (General)
• Online Access: http://umpir.ump.edu.my/id/eprint/42366/1/Intrusion%20detection%20system%20using%20autoencoder%20based.pdf; http://umpir.ump.edu.my/id/eprint/42366/2/Intrusion%20detection%20system%20using%20autoencoder%20based%20deep%20neural%20network%20for%20SME%20cybersecurity_ABS.pdf; http://umpir.ump.edu.my/id/eprint/42366/; https://doi.org/10.1109/ICICoS53627.2021.9651851

This paper proposes an intermediate solution using artificial intelligence to monitor any potential threat for SME, specifically in Malaysia. The proposed method uses Autoencoder based Deep Neural Network (AEDNN) trained with NSL-KDD dataset to efficiently detect possible cyber threats. This paper proposed AEDNN to detect automated threats cybersecurity and it does not intend to replace any existing security solutions. The proposed AEDNN is designed to detect any possible cyber threats accurately and consistently in the real-time network. The experimental results show that accurate results in the range between 96% to 99% specifically for SMEs in Malaysia.