Internet of Things (IoT) devices are well-connected; they generate and consume data which involves transmission of data back and forth among various devices. Ensuring security of the data is a critical challenge as far as IoT is concerned. Since IoT devices are inherently low-power and do not require a lot of compute power, a Network Intrusion Detection System is typically employed to detect and remove malicious packets from entering the network. In the same context, we propose feature clusters in terms of Flow, Message Queuing Telemetry Transport (MQTT) and Transmission Control Protocol (TCP) by using features in UNSW-NB15 data-set. We eliminate problems like over-fitting, curse of dimensionality and imbalance in the data-set. We apply supervised Machine Learning (ML) algorithms, i.e., Random Forest (RF), Support Vector Machine and Artificial Neural Networks on the clusters. Using RF, we, respectively, achieve 98.67% and 97.37% of accuracy in binary and multi-class classification. In clusters based techniques, we achieved 96.96%, 91.4% and 97.54% of classification accuracy by using RF on Flow & MQTT features, TCP features and top features from both clusters. Moreover, we show that the proposed feature clusters provide higher accuracy and requires lesser training time as compared to other state-of-the-art supervised ML-based approaches.

No abstract

No abstract

No abstract

Abstract:Internet communication become the need of entire world, today internet is like a recourse of power that is used to run human life. The users, as a layman, may not know that internet, a way of communication, as the use of internet is increasing also data and information that is traveling through internet is increasing by every passing day every minute. In an internet environment where every user need security about their data and information that they want to share with other, such environment requires secrecy and security to safeguard the privacy. There are many approaches available that can be adopted to provide user data security, Steganography is one of the techniques which offer sufficient platform to tackle this aspect in a suitable way. The working is very easy; the information (data) can be hidden inside the other information (data) while viewers may see the cover and hidden data will be known to intended viewers only that know the way of decryption that is adopted at sender side. In simple world two images are selected, one as cover and other as message carrier, but the view and size of original image may not be changed. This paper discusses certain technique and algorithms in context to Least Significant Bit (LSB) and ascertains possible depth of LSB usage where the distortion of image starts and attracts the attacker/ hacker. It became a unique way of information hiding by merging images with cipher data or plain text.