No abstract

No abstract

Cyber threat is growing on par with the advancements in the field of co mputer technology and information age which makes Intrusion detection Systems (IDSs) to get a lot of attention now a days. IDS is an evolv ing research area in the field of cyber security, which is aimed to detect cyber-intrusions. The authors have surveyed many research papers on IDS in the resent past and the essence of their survey is presented in this paper by keeping in thought of helping research scholars in the area of IDS. This paper aims at p resenting brief description of IDS and mach ine learning approach for its imp lementation. Though lot of literature survey on IDS exist, in this paper authors attempt to present a clear picture of IDS in all aspects through their extensive survey.

Information Security Analytics is evolving as a big trend in recent years. Lots of existing knowledge is not enough to understand it completely. In order to explore it more and to sharpen research work on it, first of all, user has to understand the importance of security. The target is on analytics which is the process of taking raw data and by processing the data and produces meaningful information through which one can derive patterns. Information security requires enthusiastic people who are interested in taking security challenges against continually evolving attacks, as opportunities to excel in the field of security. In this digital world, attacker's strategy keeps changing. They even can make use of defenders actions as a step to build a new attack. This paper proposes a new approach of applying called "protocol-specific Intrusion Detection System Using KNN Classifier" for identifying an abnormal/anomalous transaction, which leads to an attack. This can be done by submitting each observation to the model, which is already trained with some training data based on the protocol of the transaction.

No abstract

Upon application of supervised machine learning techniques Intrusion Detection Systems (IDSs) are successful in detecting known attacks as they use predefined attack signatures. However, detecting zero-day attacks is challenged because of the scarcity of the labeled instances for zero-day attacks. Advanced research on IDS applies the concept of Transfer Learning (TL) to compensate the scarcity of labeled instances of zero-day attacks by making use of abundant labeled instances present in related domain(s). This paper explores the potential of Inductive and Transductive transfer learning for detecting zero-day attacks experimentally, where inductive TL deals with the presence of minimal labeled instances in the target domain and transductive TL deals with the complete absence of labeled instances in the target domain. The concept of domain adaptation with manifold alignment (DAMA) is applied in inductive TL where the variant of DAMA is proposed to handle transductive TL due to non-availability of labeled instances. NSL_KDD dataset is used for experimentation