Summary Malware is a malicious program used for unauthorized access to organizational infrastructure and systems. To overcome challenges of exponential growth of malware, notable research has been made for unsupervised clustering of Windows‐based portable executable (PE). Nevertheless, to the best of our knowledge there has been no research for robust cluster prediction of Windows based PEs using static features. To this end, we proposed an ensemble neural network architecture for unsupervised feature learning and its distribution modeling for robust clustering of PE(s). The novel architecture is a cascaded formation of a deep autoencoder (AE) network and latent distribution modeling (LDM) network. The AE performs feature learning using latent representation and LDM performs the distribution modeling of latent representation using Gaussian approximation. An objective function is also devised for model optimization. The network adjusts the Gaussian components to optimize the distribution modeling. It also performs adjustments for data representations toward related Gaussian centers to make the model behave in adaptive manner. A novel malware dataset has also been collected by employing endpoint security management solution over enterprise network to assess proposed architecture. The dataset contains 21,486 samples including 14,497 malicious and 6989 benign ones. We also performed the evaluation of proposed architecture over publicly available benchmark malware dataset including 138,047 samples comprising 96,742 malicious and 41,323 benign PEs. The experimental results demonstrated that the proposed architecture yielded more than 95% accuracy for cluster prediction. The novel architecture has achieved superior performance and outperformed progressive techniques. The dataset along with implementation are accessible at bit.ly/3J6ZF8S .

Summary The uncontrollable spread of contagious disease COVID‐19 is a perennial threat to mankind and has resulted in an unprecedented lockdowns in several countries including Pakistan which in turn has caused an adverse socio‐economic impact to all industries. The strategic leadership and concerned state authorities are trying hard to combat and control the spread of COVID‐19 pandemic. The effective use of Information Management & Decision Support (IMDS) System can play significant role in combating pandemic and its spread, managing relief actions effectively, accessing vulnerable communities to roll out targeted subsidies by ensuring the coordinated effort and subsequent implementation. Reliable information is significantly critical to assist government and public health agencies in determining the best way forward to control this global health emergency. Therefore, this paper aims to strengthen capacity of IMDS System used by government institutions and authorities for decision making and information dissemination. In this research work, we addressed the integrity‐based issues that include completeness, correctness, and freshness of data by proposing a block chain‐based integrity protection mechanism. The proposed novel framework is a cascaded formulation of Integrity Assurance (IA) Protocol, Cryptographic Merkle Hash Tree, Digital Signature, and Blockchain. Beside cascaded formulation, two (2) schemes for MHT Generation are also presented in the framework. The proposed framework ensures fairness, completeness, and correctness of data that will be very helpful for secure data management, integration, and utilization in analysis for decision‐making. The proposed framework achieved an accuracy of more than 98.09% with better quantitative performance in standard evaluation parameters.

In recent years, VoIP (Voice over Internet Protocol) has emerged as cheap telephony medium for a long distance international and domestic calls. The number of unwanted calls from telemarketers and scammers has also risen recently, because of VoIP telephony that makes easier to initiate large number of calls without being tracing back by authorities. It is utmost important for the VoIP operators to gain trust of their customers by blocking telemarketers and scammers at the edge of the network. To address this challenge, in this paper, we present a system called Caller-Centrality that effectively identifies and blocks telemarketers/spammers without being intrusive to the caller and the callee. Caller-Centrality first models the user relationships as a caller graph and then computes reputation of the caller using weighted centrality measure. The edge weights between caller and the callee are assigned from call rate and call duration between caller and the callee. We evaluated our approach anonymized real-data set collected from a small VoIP operator. The evaluation results reveal that Caller-Centrality successfully identifies suspected telemarketers.