Anomaly Detection for malware identification using Hardware Performance\n Counters

2015/08/29 by Alberto Garcia-Serrano, Garcia-Serrano, Alberto · 1 citation
Computer Science · #Advanced Malware Detection Techniques #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.1508.07482

openalex publication_date 2015/08/29 · openalex created_date 2022/08/29 · openalex updated_date 2026/07/28

Abstract

Computers are widely used today by most people. Internet based applications,\nlike ecommerce or ebanking attracts criminals, who using sophisticated\ntechniques, tries to introduce malware on the victim computer. But not only\ncomputer users are in risk, also smartphones or smartwatch users, smart cities,\nInternet of Things devices, etc. Different techniques has been tested against\nmalware. Currently, pattern matching is the default approach in antivirus\nsoftware. Also, Machine Learning is successfully being used. Continuing this\ntrend, in this article we propose an anomaly based method using the hardware\nperformance counters (HPC) available in almost any modern computer\narchitecture. Because anomaly detection is an unsupervised process, new malware\nand APTs can be detected even if they are unknown.\n

Cited by

• A Survey of Cyber Security Countermeasures Using Hardware Performance Counters

Related

• Unsupervised Anomaly-based Malware Detection using Hardware Features
• Comprehensive Efficiency Analysis of Machine Learning Algorithms for Developing Hardware-Based Cybersecurity Countermeasures
• Defending Hardware-based Malware Detectors against Adversarial Attacks
• Malware Detection at the Microarchitecture Level using Machine Learning Techniques
• A Survey of Cyber Security Countermeasures Using Hardware Performance Counters