Adaptive secure malware efficient machine learning algorithm for healthcare data

Abstract

Malware software now encrypts the data of Internet of Things (IoT) enabled fog nodes, preventing the victim from accessing it unless they pay a ransom to the attacker. The ransom injunction is constantly accompanied by a deadline. These days, ransomware attacks are too common on IoT healthcare devices. On the other hand, IoT‐based heartbeat digital healthcare applications have been steadily increasing in popularity. These applications make a lot of data, which they send to the fog cloud to be processed further. In healthcare networks, it is critical to examine healthcare data for malicious intent. The malware is a peace code with polymorphic and metamorphic attack forms. Existing malware analysis techniques did not find malware in the content‐aware heartbeat data. The Adaptive Malware Analysis Dynamic Machine Learning (AMDML) algorithm for content‐aware heartbeat data in fog cloud computing is described in this article. Based on heartbeat data from health records, an adaptive method can train both pre‐ and post‐train malware models. AMDML is based on a rule called ‘federated learning,’ which says that malware analysis models are made at both the local fog node and the remote cloud to meet the performance workload safely. The simulation results show that AMDML outperforms machine learning malware analysis models in terms of accuracy by 60%, delay by 50%, and detection of original heartbeat data by 66% compared to existing malware analysis schemes.

GSB: GNGS and SAG-BiGRU network for malware dynamic detection

“…Yoo et al [ 29 ] proposed a machine learning-based hybrid decision model, which combined a random forest and a deep learning model to determine malware and benign files, whose experimental result achieved an 85.1% detection rate. Literature [ 30 ] proposed the Adaptive Malware Analysis Dynamic Machine Learning (AMDML) algorithm based on a rule called federated learning, which obtained better accuracy compared to the machine learning, but the accuracy is still not high and didn’t classify the malware, and the study will design a flexible environment for applications. Mazhar et al [ 31 ] proposed image-based malware classification using the VGG19 network and spatial convolutional attention, but didn’t deal with the imbalance of the data categories and lacked the exploration of the scale data, the feature engineering, and implement algorithm parallelization calculation.…”

Enhancing IoT Network Security Through Digital Object Architecture-Based Approaches

“…In contrast, the identifier primarily functions at the session layer. Nevertheless, network and channel addresses can also function as device identifiers depending on the specific task and security requirements [6].…”

Intelligent Classifiers for Football Player Performance Based on Machine Learning Models

“…G: Using a binary gender classification approach, which assigns a value of 1 to male teams and a value of 0 to female teams. Area: There are three main categories of playing positions on the field, denoted by numbers: forwards (1), defenders (2), and midfielders (3).…”

“…Machine Learning (ML) has emerged as a powerful catalyst, transforming various fields by effectively extracting valuable insights from extensive and complex datasets. Its significance goes beyond technological limitations, profoundly impacting a wide range of industries, including healthcare [1][2][3], wireless sensor networks [4,5], sports [6][7][8][9], and various other domains [10][11][12]. In the realm of football, the applications of ML can be categorized into distinct groups, as depicted in Fig.…”