An innovative malware detection methodology employing the amalgamation of stacked BiLSTM and CNN+LSTM‐based classification networks with the assistance of Mayfly metaheuristic optimization algorithm in cyber‐attack

• Published in: Concurrency and computation Vol. 35; no. 10
• Main Authors: Srinivasan, Sathiyandrakumar, Deepalakshmi, P.
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.05.2023; Wiley Subscription Services, Inc
• Subjects: Algorithms; Artificial intelligence; Bias; Brackets; classification; Combinatorial analysis; Cybersecurity; Data science; Elections; feature selection; Heuristic methods; Malware; malware detection; Networks; Neural networks; Optimization; pre‐processing; Recall; Transfer functions
• ISSN: 1532-0626; 1532-0634
• DOI: 10.1002/cpe.7679

Summary The propagation of bias and its data have sensitive and critical security enterprises, which emphasizing the significance of perfecting state‐of‐the‐art intrusion discovery systems. These days malware pitfalls have turned precipitously vigorous, intricate and independently on this bias and its data. The artificial intelligence approaches have turned into the focus for cybersecurity as these are noticed acting as more applicable for dealing with contemporary malware events. Particularly, the neural networks having its robust conception prosecution which capability can challenge an expansive range of cyber pitfalls. This article portrays the advancement and testing of a neural network for bracket procedures. Also, the point election could be regarded as a combinatorial optimization issue. It also includes a new point selection fashion known as the Mayfly metaheuristic algorithm, which incorporates an S‐shaped transfer function for converting it into a double variant of the Mayfly Algorithm. While distinct seeker results were acquired out of different areas of the hunt space employing the Mayfly Algorithm, a lesser result could be assured. also, there are two bracket networks like piled BiLSTM and CNN LSTM that are regarded for the UNSW‐NB15 dataset, which automatically learn features out of the undressed data for landing the vicious train structure patterns and law sequence patterns. This largely lessens the price of artificial features engineering. The proffered bracket networks are examined employing the criteria like accuracy, precision, recall, F1‐score, and AUC score under binary and multi classes. It is observed that the proffered bracket networks achieve 91.87 of accuracy, 92.769 of precision, 90.47 of recall, and 91.6 of F1‐ score.