MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

Cyber-security is unavoidable in present days due to the security importance of each and every digital device part of a global network among millions of computing nodes. Industry 4.0 created much more impact on the automation of industrial micro functionalities to the manufacturing level, with more sensitive data to handle at every stage of organization, then security features of such platform are more important for a complete smooth working environment. This article will elaborate more on an understanding of Incremental learning with data analysis of huge Cyber-attack detection datasets which consist of Adware, Ransomware, SMS malware, scareware, Benign..etc. Incremental learning refers to a group of scalable various algorithms that as the ability to learn in terms of sequentially and can continuously update their models from huge infinite data streams. This working model helps to understand by adopting dynamic learning for varying incoming data inputs based on huge dataset inputs with scalable learning models of algorithms without discarding learned model outcomes. Number of incremental classification model were used where as ARFC gives very good results with higher accuracy, precision, recall, and f1-score values. The results revealed that the proposed model training generates a complete result by adopting variation in dynamic inputs which helps to improve classification higher accuracy by comparing with other training models. © 2022 IEEE.

World University root node

School of Computer Engineering & Technology

Engineering and Technology

Proceedings - 2022 2nd International Conference on Innovative Sustainable Computational Technologies, CISCT 2022

Streamed Incremental Learning for Cyber Attack Classification using Machine Learning

Opportunistic network does not rely on any pre-existing infrastructure and no assumption is made on the existence of a complete path between source and destination. The development of efficient routing protocols for opportunistic networks is generally a difficult task due to the absence of knowledge about the network topology. Therefore, routing is one of the most persuasive challenges of opportunistic networks. In this chapter, we give the general definition of context information and emphasize the role of context information to take forwarding decisions in opportunistic networks. We classify the main routing protocols proposed in the literature on the basis of context information of users they exploit. Specifically, we classify two main classes of routing protocols, corresponding to context-oblivious and context-aware protocols. Then, we further classify context-aware routing protocols into two subclasses, i.e., partially context-aware and fully context-aware protocols, based on the amount of context information they use for routing. We emphasize and describe only routing protocols of context-aware category and the detailed discussion about context-oblivious routing protocols is out of the scope of this chapter.