IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 23, Issue 4, Ser. I (Jul. –Aug. 2021), PP 55-60 www.iosrjournals.org DOI: 10.9790/0661-2304015560 www.iosrjournals.org 55 | Page Investigation and Classification of Cyber Crime using Deep Learning Prof. Ms. A. B. Bavane 1 , Aishwarya Chavan 2 , Mayuri Gaikwad 3 , Varsha Khillare 4 , Sonali Kolekar 5 1 Asstt. Prof. Department of Information Technology, DVVP COE Ahmednagar, Maharashtra, India 2,3,4,5 Department of information Technology, DVVP COE Ahmednagar, Maharashtra, India Abstract: An intrusion detection system is software that monitors a single or a network of computers for malicious activities that are aimed at stealing or censoring information or corrupting network protocols. Most technique used in today’s intrusion detection system are not able to deal with the dynamic and complex nature of cyber-attacks on computer networks. Even though efficient adaptive methods like various techniques of Deep learning can result in higher detection rates, lower false alarm rates and reasonable computation and communication cost. With the use of data mining can result in frequent pattern mining, classification, clustering and mini data stream. An advanced method for intrusion detection system based on Data mining and Deep Learning is proposed in this proposal. Intrusion Detection system is divided into two types Host based IDS and Network based IDS. In this proposal, Network based IDS is used to protect computer network and its resources from malicious attacks. Based on the number of citations or the relevance of an emerging method, papers representing each method were identified, read, and summarized. Because data are so important in Deep learning and data mining approaches, well-known cyber data sets are used in Deep learning and data mining. Key Word: Cyber Crime, Deep Learning, Data mining, Intrusion Detection System. --------------------------------------------------------------------------------------------------------------------------------------- Date of Submission: 10-07-2021 Date of Acceptance: 26-07-2021 --------------------------------------------------------------------------------------------------------------------------- I. Introduction Cyber security systems are composed of network security systems and computer security systems. Each of these has, at a minimum, a firewall, antivirus software, and an intrusion detection system .Intrusion detection system s help discover, determine, and identify unauthorized use, duplication, alteration, and destruction of information systems. The security breaches include external intrusions attacks from outside the organization and internal intrusions. Recommendation The Deep learning, Data Mining methods are described, as well as several applications of each method to cyber intrusion detection problems. The complexity of different Deep learning and data mining algorithms is discussed, and the proposal provides a set of comparison criteria for Deep learning and data mining methods and a set of recommendations on the best methods to use depending on the characteristics of the cyber Problem to solve Cyber security is the set of technologies and processes designed to protect computers, networks, programs, and data from attack, unauthorized access, change, or destruction. There are three main types of cyber analytics in support of intrusion detection systems: misuse-based, anomaly-based, and hybrid. Misuse-based techniques are designed to detect known attacks by using signatures of those attacks. They are effective for detecting known type of attacks without generating an overwhelming number of false alarms. They require frequent manual updates of the database with rules and signatures. Misuse-based techniques cannot detect novel attacks. Anomaly-based techniques model the normal network and system behavior, and identify anomalies as deviations from normal behavior. They are appealing because of their ability to detect zero-day attacks. Another advantage is that the profiles of normal activity are customized for every system, application, or network, thereby making it difficult for attackers to know which activities they can carry out undetected. Additionally, the data on which anomaly-based techniques alert can be used to define the signatures for misuse detectors. The main disadvantage of anomaly-based techniques is the potential for high false alarm rates because previously unseen system behaviors may be categorized as anomalies. Use of Internet services are increasing day by day the threats from the internet to computer systems, data are also increasing. Attackers can easily get access to the important data resources in our systems. It is very important to protect the data from such attackers as they can use this data for their personal needs and can sell the data for their personal needs or it can end up in wrong hands. Large amount of data is stored in the servers and computers of companies. So it is very important to make sure the valuable data is safe and secure. This can be done with the help of real time Intrusion detection system which detects any kind of suspicious activity and