• MALA K
• RANJITHA H N
• ROOPA R

Cloud computing (CC) is the rapidly evolving landscape of IT. It focuses on implementing intrusion detection systems (IDS) leveraging deep learning (DL) methodologies. Utilizing hierarchical long short-term memory (HLSTM), the study evaluates its efficacy for feature selection via variance threshold-based regression (VTR) on Bot-IoT and NSL-KDD datasets, achieving notable accuracies of 99.50% and 0.995, respectively. Comparative analysis against existing methods highlights the superiority of DL-based IDS. Additionally, a deep learning model for network intrusion detection (DLNID) is proposed, integrating attention mechanism and bidirectional long short-term memory (Bi-LSTM) networks, surpassing other methods with accuracies of 90.73% and 89.65% on the NSL-KDD dataset. Furthermore, a novel network intrusion detection method combining CNN and Bi-LSTM networks is introduced, achieving an average accuracy improvement to 95.50% and notable reductions in false- positive rate, underscoring the efficacy of DL-based approaches in enhancing intrusion detection performance amidst escalating network threats.

Intrusion detection, deep learning, CNN, RNN, Bi-LSTM.

"INTRUSION DETECTION IN CLOUD COMPUTING NETWORK USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.e800-e804, April-2024, Available :http://www.jetir.org/papers/JETIR2404489.pdf

"INTRUSION DETECTION IN CLOUD COMPUTING NETWORK USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppe800-e804, April-2024, Available at : http://www.jetir.org/papers/JETIR2404489.pdf