Protecting from Malware Obfuscation Attacks through Adversarial Risk\n Analysis

2019/11/09 by Alberto J. Redondo, Redondo, Alberto, David Rı́os Insua +1
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1911.03653

openalex publication_date 2019/11/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Malware constitutes a major global risk affecting millions of users each\nyear. Standard algorithms in detection systems perform insufficiently when\ndealing with malware passed through obfuscation tools. We illustrate this\nstudying in detail an open source metamorphic software, making use of a hybrid\nframework to obtain the relevant features from binaries. We then provide an\nimproved alternative solution based on adversarial risk analysis which we\nillustrate describe with an example.\n

Related

• FEEBO: An Empirical Evaluation Framework for Malware Behavior Obfuscation
• Malfustection: Obfuscated Malware Detection and Malware Classification with Data Shortage by Combining Semi-Supervised and Contrastive Learning
• Use of Cryptography in Malware Obfuscation
• Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach
• Obfuscated Malware Detection: Investigating Real-world Scenarios through Memory Analysis