CharBot: A Simple and Effective Method for Evading DGA Classifiers
This work highlights a critical vulnerability in real-time DGA classifiers for cybersecurity, demonstrating that they are inherently susceptible to adversarial attacks if relying solely on domain name strings, which is an incremental but important finding for improving malware detection robustness.
The authors tackled the problem of evading domain generation algorithm (DGA) classifiers used in malware detection by introducing CharBot, a novel DGA that generates domain names undetected by state-of-the-art classifiers like FANCI and LSTM.MI, showing that retraining these classifiers is ineffective as a defense.
Domain generation algorithms (DGAs) are commonly leveraged by malware to create lists of domain names which can be used for command and control (C&C) purposes. Approaches based on machine learning have recently been developed to automatically detect generated domain names in real-time. In this work, we present a novel DGA called CharBot which is capable of producing large numbers of unregistered domain names that are not detected by state-of-the-art classifiers for real-time detection of DGAs, including the recently published methods FANCI (a random forest based on human-engineered features) and LSTM.MI (a deep learning approach). CharBot is very simple, effective and requires no knowledge of the targeted DGA classifiers. We show that retraining the classifiers on CharBot samples is not a viable defense strategy. We believe these findings show that DGA classifiers are inherently vulnerable to adversarial attacks if they rely only on the domain name string to make a decision. Designing a robust DGA classifier may, therefore, necessitate the use of additional information besides the domain name alone. To the best of our knowledge, CharBot is the simplest and most efficient black-box adversarial attack against DGA classifiers proposed to date.