Browsing by Author "Ankit Jain, Anita Shukla, Vivek Kumar, Imran Ullah Khan, Keshav Kumar, Kamini Simi Bajaj"

Now showing 1 - 1 of 1

Exploring Emerging Techniques and Tools for Malware Analysis
(Apple Academic Press, STEM, 2026) Ankit Jain, Anita Shukla, Vivek Kumar, Imran Ullah Khan, Keshav Kumar, Kamini Simi Bajaj
One of the largest problems facing the Internet today is the vast volume of data and files that must be analysed for potential malicious intent. according to the constantly changing field of cybersecurity. Malware, or malicious software, is getting more and more complex and frequently uses metamorphic and polymorphic approaches. These features make it possible for malware to alter its code structure while spreading, which makes detection very difficult. Because they frequently miss previously undiscovered or zero-day malware variants, traditional defensive mechanisms especially those that depend on signature-based detection are proving to be inadequate in the fight against these threats. To properly identify and lessen the impact of malware families, sophisticated analytical techniques are required due to their increasing diversity and complexity. Even though malware is always evolving, many versions from the same family have behavioral patterns that are indicative of their origin and underlying purpose. Either static analysis, which examines code without execution, or dynamic analysis, which watches malware run in a controlled environment, can be used to find these behavioral characteristics. Machine learning (ML) approaches have become effective tools for the categorization and detection of unknown malware by utilizing these behavioral traits. Labelled datasets can be used to train machine learning algorithms to identify common patterns in known malware families. These algorithms can then use this information to identify new, hidden threats. The accuracy and adaptability of detection have been greatly increased by this paradigm shift from signature-based to behaviour-based and machine learning-driven analysis. An extensive review of the newest methods and resources for malware analysis is provided in this survey article. It focuses on comparing and contrasting modern and traditional approaches, emphasizing their advantages, disadvantages, and suitability for practical situations. Particular attention is paid to how machine learning might improve malware detection skills and how contemporary solutions include these intelligent algorithms to tackle the problems caused by malware that is polymorphic and metamorphic. The significance of integrating static and dynamic analysis techniques to create resilient, hybrid detection models that can successfully combat the constantly shifting malware field is also covered in the article.