• Beulah A
• Samundiswary P

The Internet of Things (IoT) has increased significance in the modern period as a result of rapid development in the technology in several ways. The popularity of IoT applications has increased in comparison to earlier times due to the availability of several devices that act as IoT enablers, such as smartwatches, smartphones, security cameras, and smart sensors. However, a number of issues, such as Distributed Denial-of-Service (DDoS) assaults, have been brought on by the absence of security in IoT devices. Many efforts have been made recently to develop intelligent models that can protect IoT networks from DDoS attacks. Making a model that can fight against DDoS attacks and be able to differentiate between legitimate traffic and false alarms is the main topic of research that is still being done. The most popular moniker for distributed network attacks is DDoS attacks. These attacks take advantage of limitations including the layout of the website run by the authorised organisation and arrangement of asset. To determine the current state of DDoS attacks, the University of California Irvine (UCI) machine learning respiratory dataset must be used. Further, Deep learning algorithms are typically used to categorise and forecast the many forms of DDoS attacks. In Existing Method XG Boost is used and performance metrices are analysed. However, the accuracy is not good. Hence in this paper, Long Short-Term Memory (LSTM) method based Recurrent Neural Network (RNN) algorithm is developed for the detection of DDoS attack which is considered as the proposed work. LSTM achieves precision (PR), recall (RE) and F1 score of approximately 99%. Additionally, the above-mentioned technique achieves an Accuracy (AC) of roughly 94%.

Distributed Denial-of-Service (DDOS) attacks, Internet of Things, Deep Learning, classification, Recurrent Neural Network, Long Short-Term Memory.

"PREDICTION OF DDOS ATTACK USING LSTM TECHNIQUE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.j200-j204, May-2023, Available :http://www.jetir.org/papers/JETIR2305977.pdf

"PREDICTION OF DDOS ATTACK USING LSTM TECHNIQUE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppj200-j204, May-2023, Available at : http://www.jetir.org/papers/JETIR2305977.pdf