IoT devices with weak security designs are a serious threat to organizations. They are the building blocks of Botnets, the platforms that launch organized attacks that are capable of shutting down an entire infrastructure. Researchers have been developing IDS solutions that can counter such threats, often by employing innovation from other disciplines like artificial intelligence and machine learning. One of the issues that may be encountered when machine learning is used is dataset purity. Since they are not captured from perfect environments, datasets may contain data that could affect the machine learning process, negatively. Algorithms already exist for such problems. Repeated Edited Nearest Neighbor (RENN), Encoding Length (Explore), and Decremental Reduction Optimization Procedure 5 (DROP5) algorithm can filter noises out of datasets. They also provide other benefits such as instance reduction which could help reduce larger Botnet datasets, without sacrificing their quality. Three datasets were chosen in this study to construct an IDS: IoTID20, N-BaIoT and MedBIoT. The filtering algorithms, RENN, Explore, and DROP5 were used on them to filter noise and reduce instances. Noise was also injected and filtered again to assess the resilience of these filters. Then feature optimizations were used to shrink the dataset features. Finally, machine learning was applied on the processed dataset and the resulting IDS was evaluated with the standard supervised learning metrics: Accuracy, Precision, Recall, Specificity, F-Score and G-Mean. Results showed that RENN and DROP5 filtering delivered excellent results. DROP5, in particular, managed to reduce the dataset substantially without sacrificing accuracy. However, when noise got injected, the DROP5 accuracy went down and could not keep up. Of the three dataset, N-BaIoT delivers the best accuracy overall across the learning techniques.

The Android operating system is the most used mobile operating system in the world, and it is one of the most popular operating systems for different kinds of devices from smartwatches, IoT, and TVs to mobiles and cockpits in cars. Security is the main challenge to any operating system. Android malware attacks and vulnerabilities are known as emerging risks for mobile devices. The development of Android malware has been observed to be at an accelerated speed. Most Android security breaches permitted by permission misuse are amongst the most critical and prevalent issues threatening Android OS security. This research performs several studies on malware and non-malware applications to provide a recently updated dataset. The goal of proposed models is to find a combination of noise-cleaning algorithms, features selection techniques, and classification algorithms that are noise-tolerant and can achieve high accuracy results in detecting new Android malware. The results from the empirical experiments show that the proposed models are able to detect Android malware with an accuracy that reaches 87%, despite the noise in the dataset. We also find that the best classification results are achieved using the RF algorithm. This work can be extended in many ways by applying higher noise ratios and running more classifiers and optimizers.