Drug repurposing (or repositioning) is the process of finding new therapeutic uses for drugs already approved by drug regulatory authorities (e.g., the Food and Drug Administration (FDA) and Therapeutic Goods Administration (TGA)) for other diseases. This involves analysing the interactions between different biological entities, such as drug targets (genes/proteins and biological pathways) and drug properties, to discover novel drug–target or drug–disease relations. Machine learning and deep learning models have successfully analysed complex heterogeneous data with applications in the biomedical domain, and have also been used for drug repurposing. This study presents a novel unsupervised machine learning framework that utilizes a graph-based autoencoder for multi-feature type clustering on heterogeneous drug data. The dataset consists of 438 drugs, of which 224 are under clinical trials for COVID-19 (category A). The rest are systematically filtered to ensure the safety and efficacy of the treatment (category B). The framework solely relies on reported drug data, including its pharmacological properties, chemical/physical properties, interaction with the host, and efficacy in different publicly available COVID-19 assays. Our machine-learning framework revealed three clusters of interest and provided recommendations featuring the top 15 drugs for COVID-19 drug repurposing, which were shortlisted based on the predicted clusters that were dominated by category A drugs. Our framework can be extended to support other datasets and drug repurposing studies with the availability of our open-source code.

Cybercriminals who interact extensively on underground forums, often, exchange illegal commodities and indulge in discussions on unwarranted topics. To facilitate the disruption of these highly proficient criminals, we propose a deep learning based multi-relational graph convolutional network approach to analyse the underground forum and identify key actors. We first modeled the hackforum into a homogeneous graph of users, where the multiple edges between users are captured based on their involvement in private conversations, group discussions and other miscellaneous activities. In addition, we also encode the textual content shared among users’ in form of distributed feature representation generated from BERT. To obtain ground truth labels for training data, we propose a hypothesis to calculate the scores for each user based on the quality and quantity of their involvement in the underground forum. The proposed framework jointly embeds the users’ and multi relational information to learn the nodes embeddings in the graph. We demonstrate the effectiveness of the proposed model on a neonazi underground forum, Iron March. We conducted an ablation study on the model parameters to generate the best results and achieved a classification accuracy of 82% which validates the proposed hypothesis for score computation and class labelling. To establish the robustness of our model, we compare its performance against state-of-art models. Though we used an underground forum as a showcase, the proposed model can be implemented to identify influential users’ on other social media platforms.

Cyber threat intelligence (CTI) can be gathered from multiple sources, and Twitter is one such open source platform where a large volume and variety of threat data is shared every day. The automated and timely mining of relevant threat knowledge from this data can be crucial for enrichment of existing threat intelligence platforms to proactively defend against cyber attacks. We propose CTI-Twitter: a novel frame-work combining supervised and unsupervised learning models to collect, process, analyze and generate threat specific knowledge from tweets coming from multiple users. CTI-Twitter has multi-fold contributions: i) first collecting tweets through Twitter API, ii) extracting relevant threat tweets from irrelevant ones, and classifying relevant ones into multiple classes of threats iii) then grouping tweets belonging to each class using topic modeling iv) finally performing data enrichment and verification process. We evaluate our proposed model on real-time tweets collected for about four months (in year 2020) using Twitter API. The encouraging results obtained indicate the effectiveness of CTI-Twitter in terms of timeliness and discovery of trending attacks patterns, and vulnerabilities.

Android malware has become the topmost threat for ubiquitous and useful Android eco-system. Multiple solutions leveraging big data and machine learning capabilities to detect android malware are being constantly developed. Too often, many of these solutions are either limited to the research output or remain isolated and unable to reach to end-users or malware researchers. In this paper, we propose, PACE, a unified solution to offer open and easy implementation access to several machine learning-based Android malware detection techniques that make most of the research in this domain reproducible. The benefits of PACE are offered using three interfaces i.e. through REST API, Web Interface and ADB interface. Multiple interfaces enable users with different expertise such as IT administrator, security practitioners, malware researcher, etc. to avail its offered services. A community-accepted dataset is used for testing of all the techniques to provide a better comparison of performance. A prototype of the proposed platform is introduced and our vision is that it will help malware analysts to tackle challenges and reduce the amount of manual work.

Besides the notion of friendship, trust or support in social networking sites (SNSs), quite often social interactions also reflect users' antagonistic attitude towards each other. Thus, the hidden knowledge contained in social network data can be considered as an important resource to discover the formation of such positive and negative links. In this work, an inductive learning framework is presented to suggest 'friends' and 'foes' links to individuals which envisage the social balance among users in the corresponding friends and foes networks (FFN). First we learn a model by applying C4.5, the most widely adopted decision tree based classification algorithm, to exploit the feature patterns presented in the users' FFN and utilizing it to further predict friend/foe relationship of unknown links. Secondly, a quantitative measure of social balance, balance index, is used to support our decision on the recommendation of new friends and foes links (FFL) to avoid possible imbalance in the extended FFN with newly suggested links. The proposed scheme ensures that the recommendation of new FFLs either maintains or enhances the balancing factor of the existing FFN of an individual. Experimental results show the effectiveness of our proposed schemes.