China
Africa
Explore chapters and articles related to this topic
Malware Detection and Mitigation
Published in Nicholas Kolokotronis, Stavros Shiaeles, Cyber-Security Threats, Actors, and Dynamic Mitigation, 2021
Gueltoum Bendiab, Stavros Shiaeles, Nick Savage
Detection systems usually include two main stages: malware analysis and detection. Malware analysis is the process of studying malicious software with the intention of having a better understanding of several aspects of malware like malware behavior, evolution over time their selected victims, and how they are controlled. It was defined by security experts as “the art of dissecting malware to understand how it works, how to identify it, and how to defeat or eliminate it” [9]. Such analysis should help security firms to understand the impact that can occur from malware attacks and it should enable them to develop effective detection and mitigation techniques. In the early days of cyber-security, malware analysis was conducted manually by human analysts. It was a time-consuming process and error prone.
Malware classification using neural network
Published in Sangeeta Jadhav, Rahul Desai, Ashwini Sapkal, Application of Communication Computational Intelligence and Learning, 2022
Deeptanshu Singh Rathore, Ashwini Sapkal, Geeta Patil, Rahul Desai, Aparna Joshi
Malware detection is the process of determining if a binary executable is benign or malicious, whereas malware classification is the process of determining which malware class it belongs to. Malware analysis can be done using two ways, static analysis and dynamic analysis, depending on the state of the studied malware. The term ‘static analysis’ refers to the process of analysing a programme without running it. Static analysis has the advantage of being able to quickly identify an author’s style and profile the code flow, but it also has the disadvantage of being easily defeated by obfuscation techniques. This strategy devotes time to both debugging and tracking the software. As a result, when compared to static analysis, dynamic analysis is frequently inefficient.
Evolution of Deep Quantum Learning Models Based on Comprehensive Survey on Effective Malware Identification and Analysis
Published in Thiruselvan Subramanian, Archana Dhyani, Adarsh Kumar, Sukhpal Singh Gill, Artificial Intelligence, Machine Learning and Blockchain in Quantum Satellite, Drone and Network, 2023
S. Poornima, Thiruselvan Subramanian
For developing an ML model, malware of a similar type are clustered in a group since it exists in various forms. They are divided based on their harness, as they can exist in more classes. Therefore, malware analysis is derived from the detection procedure to identify the complete sustainability of malware. To analyze the malware, its functionalities, effects, and motivation, malware analysis is a much-needed step that helps the programmer design anti-malware software. Based on the tools and algorithms adopted, malware analysis is partitioned into three classes and shown in Figures 6.5 and 6.6.
Scalable Malware Detection System Using Distributed Deep Learning
Published in Cybernetics and Systems, 2023
Malware is always changing, employing a complicated and sneaky strategy. New forms of malware emerge on a regular basis, each with more dangerous qualities than the one before it. The ever-increasing complexity of malware makes it difficult for analysts to detect it. Attackers are constantly developing new and advanced techniques to avoid detection (S. Gupta 2019; Machine Learning for Malware Detection n.d.; Moussas and Andreatos 2021). This is where malware analysis comes in handy. Understanding the malware’s strategy to infection, threat, danger, and associated destructive elements are the key goals of malware analysis. To analyze malware, a variety of methods and techniques are required. Better analysis can aid in the development of more effective defensive strategies for the organization (Yuxin and Siyi, 2017; de Paola et al. 2018; Yuan et al. 2014). For malware analysis, there are several approaches (Figure 1), with static malware analysis and dynamic malware analysis being the most common and well-known.
On the Effectiveness of Image Processing Based Malware Detection Techniques
Published in Cybernetics and Systems, 2022
According to a report by cybersecurity company Deep Instinct, the number of malware attacks has increased by 358% compared to 2019, and cybercrimes cost $2.9 million per minute (Cyber Threat Report 2021). According to another report, Check Point warrants that the world comes across about 100,000 malicious websites and 10,000 malware files every day (Check Point Report 2021). Developing efficient methods to detect and counteract malware is an indispensable responsibility, and malware analysis is typically done to provide the cybersecurity professional with useful information to react to potential attacks. When analyzing the samples, it is anticipated that the analyst can figure out exactly what the binary is doing, how to identify them in the network, and how to evaluate its impact and possible expansion. Signature-based anti-virus scanners are the typical protection machinery utilized against malware today. They recognize malicious samples by comparing the set of existing signatures with the new samples. The signature generation is usually tedious, error-prone exercise carried out manually and fail to detect zero day malware.
Anti-malware engines under adversarial attacks
Published in International Journal of Computers and Applications, 2022
Shymalagowri Selvaganapathy, Sudha Sadasivam
Techniques to provide protection against malware consist of an analysis phase followed by detection phase [1]. Malware analysis can be classified into static, dynamic and hybrid techniques. In static analysis, the source code is examined without executing the code. Static information about the executable like header data and byte sequences are analyzed to observe the entire execution path. Although swift and scalable, static analysis is highly ineffective as it is not capable of handling malware utilizing obfuscation techniques [2]. Dynamic analysis involves analyzing an application during its execution. The application is executed on a real device or a virtual environment [3]. Dynamic analysis has the drawback of being vulnerable to malware that uses environment aware approaches [4]. Hybrid approach takes in features from both static and dynamic techniques to build its feature set for malware detection [5].