Smart contracts offer automation for various decentralized applications but suffer from vulnerabilities that cause financial losses. Detecting vulnerabilities is critical to safeguarding decentralized applications before deployment. Automatic detection is more efficient than manual auditing of large codebases. Machine learning (ML) has emerged as a suitable technique for vulnerability detection. However, a systematic literature review (SLR) of ML models is lacking, making it difficult to identify research gaps. No published systematic review exists for ML approaches to smart contract vulnerability detection. This research focuses on ML-driven detection mechanisms from various databases. 46 studies were selected and reviewed based on keywords. The contributions address three research questions: vulnerability identification, machine learning model approaches, and data sources. In addition to highlighting gaps that require further investigation, the drawbacks of machine learning are discussed. This study lays the groundwork for improving ML solutions by mapping technical challenges and future directions.

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.