Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection

Abstract

In this paper, we introduce and evaluate PROPEDEUTICA 1 , a novel methodology and framework for efficient and effective real-time malware detection, leveraging the best of conventional machine learning (ML) and deep learning (DL) algorithms.In PROPEDEUTICA, all software processes in the system start execution subjected to a conventional ML detector for fast classification. If a piece of software receives a borderline classification, it is subjected to further analysis via more performance expensive and more accurate DL methods, via our newly proposed DL algorithm DEEPMALWARE. Further, in an exploratory fashion, we introduce delays to the execution of software subjected to DEEPMALWARE as a way to "buy time" for DL analysis and to rate-limit the impact of possible malware in the system.We evaluated PROPEDEUTICA with a set of 9,115 malware samples and 877 commonly used benign software samples from various categories for the Windows OS. Our results show that the false positive rate for conventional ML methods can reach 20%, and for modern DL methods it is usually below 6%. However, the classification time for DL can be 100X longer than conventional ML methods. PROPEDEUTICA improved the detection F1-score from 77.54% (conventional ML method) to 90.25% (16.39% increase), and reduced the detection time by 54.86%. Further, the percentage of software subjected to DL analysis was approximately 40% on average. Further, the application of delays in software subjected to ML reduced the detection time by approximately 10%. Finally, we found and discussed a discrepancy between the detection accuracy offline (analysis after all traces are collected) and on-the-fly (analysis in tandem with trace collection). Conventional ML experienced a decrease of 13% in accuracy when executed offline (89.05%) compared to online (77.54%) with the same traces.Our insights show that conventional ML and modern DLbased malware detectors in isolation cannot meet the needs of efficient and effective malware detection: high accuracy, low false positive rate, and short classification time.

Adversarial Examples: Attacks and Defenses for Deep Learning

“…Deep learning has been used in static and behavioral-based malware detection due to its capability of detecting zeroday malware [14]- [17]. Recent studies generated adversarial malware samples to evade deep learning-based malware detection [101]- [103], [105].…”

“…Apple also provides face authentication to unlock mobile phones [13]. Behavior-based malware detection and anomaly detection solutions are built upon deep learning to find semantic features [14]- [17].…”