Threat Modeling for Machine Learning-Based Network Intrusion Detection Systems

Network Intrusion Detection Systems (NIDS) monitor networking environments for suspicious events that could compromise the availability, integrity, or confidentiality of the network’s resources. To ensure NIDSs play their vital roles, it is necessary to identify how they can be attacked by adopting a viewpoint similar to the adversary to identify vulnerabilities and defenses hiatus. Accordingly, effective countermeasures can be designed to thwart any potential attacks. Machine learning (ML) approaches have been adopted widely for network anomaly detection. However, it has been found that ML models are vulnerable to adversarial attacks. In such attacks, subtle perturbations are inserted to the original inputs at inference time in order to evade the classifier detection or at training time to degrade its performance. Yet, modeling adversarial attacks and the associated threats of employing the machine learning approaches for NIDSs was not addressed. One of the growing challenges is to avoid ML-based systems’ diversity and ensure their security and trust. In this paper, we conduct threat modeling for ML-based NIDS using STRIDE and Attack Tree approaches to identify the potential threats on different levels. We model the threats that can be potentially realized by exploiting vulnerabilities in ML algorithms through a simplified structural attack tree. To provide holistic threat modeling, we apply the STRIDE method to systems’ data flow to uncover further technical threats. Our models revealed a noticing of 46 possible threats to consider. These presented models can help to understand the different ways that a ML-based NIDS can be attacked; hence, hardening measures can be developed to prevent these potential attacks from achieving their goals.

I. Introduction

The complexity of cyber attacks against all networking environments is developing rapidly. A network intrusion detection system (NIDS) is still the first line of defense against cyber attacks. The NIDS monitors and analyzes network traffic for malicious activities such as denial of service attacks, probing, information theft, and port scanning [1]. It utilizes two major methodologies to detect malicious activities: signature-based or anomaly-based [1]. A signature-based NIDS (i.e., misuse detection) identifies intrusions by comparing the network traffic to predefined patterns of known attacks with very low false alarms. The significant disadvantage of this approach is that it fails at detecting zero-day attacks. An anomaly-based NIDS (i.e., behavior-based) utilizes machine learning approaches to detect anomalies and novel attacks by comparing the network packets to a profile of benign traffic in order to discover any deviation from the norm.