• AGARSHA MERIN JOHN
• DIVYA JAMES

Intrusion Detection System (IDS) can distinguish rising assaults and a few peculiarity discovery plans. There is a need to ensure against any irregular practices and assaults that endeavor to damage the respectability, classification or accessibility of valuable data. The vast majority of the intrusion detection system uses information mining or AI methods to get familiar with the contrasts among ordinary and vindictive practices. The profound learning strategies in the intrusion detection system (IDS) can be utilized to improve detection and can accomplish higher characterization precision and secure the system from different sorts of assaults. The AI calculations that can be utilized to identify precious assaults are support vector machines (SVMs), K-NN. These AI classifiers can be utilized to foresee between two potential results (for example vindictive and non-noxious system traffic). In Deep learning, a Deep neural system (DNN) can be utilized to create a successful intrusion detection system to identify and characterize capricious digital assaults and perform better in contrast with AI classifiers. This venture proposes an examination between various sorts of deep learning calculations dependent on exactness, review, and precision with various datasets.

Machine Learning, Deep Learning, Intrusion Detection system.

"DEEP NEURAL NETWORK MODEL FOR INTRUSION DETECTION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 2, page no.482-488, February-2020, Available :http://www.jetir.org/papers/JETIR2002072.pdf

"DEEP NEURAL NETWORK MODEL FOR INTRUSION DETECTION SYSTEM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 2, page no. pp482-488, February-2020, Available at : http://www.jetir.org/papers/JETIR2002072.pdf