Flow-based Detection and Proxy-based Evasion of Encrypted Malware C2 Traffic

Abstract

State of the art deep learning techniques are known to be vulnerable to evasion attacks where an adversarial sample is generated from a malign sample and misclassified as benign. Detection of encrypted malware command and control traffic based on TCP/IP flow features can be framed as a learning task and is thus vulnerable to evasion attacks. However, unlike e.g. in image processing where generated adversarial samples can be directly mapped to images, going from flow features to actual TCP/IP packets requires crafting the sequence of packets, with no established approach for such crafting and a limitation on the set of modifiable features that such crafting allows. In this paper we discuss learning and evasion consequences of the gap between generated and crafted adversarial samples. We exemplify with a deep neural network detector trained on a public C2 traffic dataset, white-box adversarial learning, and a proxy-based approach for crafting longer flows. Our results show 1) the high evasion rate obtained by using generated adversarial samples on the detector can be significantly reduced when using crafted adversarial samples; 2) robustness against adversarial samples by model hardening varies according to the crafting approach and corresponding set of modifiable features that the attack allows for; 3) incrementally training hardened models with adversarial samples can produce a level playing field where no detector is best against all attacks and no attack is best against all detectors, in a given set of attacks and detectors. To the best of our knowledge this is the first time that level playing field feature set-and iteration-hardening are analyzed in encrypted C2 malware traffic detection. CCS CONCEPTS • Security and privacy → Intrusion/anomaly detection and malware mitigation; • Computing methodologies → Machine learning.

ML-based tunnel detection and tunneled application classification

“…We do not present results for elapsed time since the start of the flow because its results are worse than IAT. Previous work [33] show that tampering with IAT and elapsed time since the flow start using a proxy yields a performance decrease. We thus only consider packet size with direction and byte burst as relevant features for the remainder of the paper.…”

The Threat of Offensive AI to Organizations

“…Generation This is the task of creating content that fits a target distribution which, in some cases, requires realism in the eyes of a human. Examples of generation for offensive uses include the tampering of media evidence [155,192], intelligent password guessing [75,89], and traffic shaping to avoid detection [85,166]. Deepfakes are another instance of offensive AI in this category.…”

“…AI-based tools are programs which performs a specific task in adversary's arsenal. For example, a tool for intelligently predicting passwords [75,89], obfuscating malware code [59], traffic shaping for evasion [85,121,166], puppeting a persona [154], and so on. These tools are typically in the form of a machine learning model.…”

“…Bots trying to contact their C2 server can generate URLs that appear legitimate to humans [175], or that can evade malicious-URL detectors [208]. To evade traffic-based NIDSs, adversaries can shape their traffic [85,166] or change their timing to hide it [200].…”

“…Surprisingly, both academia and industry consider the use of AI for stealth as the least threatening OAC category in general. Even though there has been a great deal of work showing how IDS models are vulnerable [166,213], IDS evasion approaches were considered the second most defeatable OAC after intelligent scanning. This may have to do with the fact that the adversary cannot evaluate its AI-based evasion techniques inside the actual network, and thus risks detection.…”