"What is the Problem Space?" Defining Host-space Adversarial Perturbations against Network Intrusion Detection Systems

Abstract

Network Intrusion Detection Systems (NIDS) are now increasingly leveraging Machine Learning (ML) techniques to detect malicious network activities. Numerous papers have scrutinized the security of ML-based NIDS (ML-NIDS) by testing them against various attacks involving adversarial perturbations. The findings were oftentimes worrying: by making imperceptible changes to a given input, powerful ML models would be bypassed. In this context, we took a step back and wondered: where (i.e., in what “space”) have these perturbations been applied? We argue that real-world adversaries can apply adversarial perturbations only by operating on the hosts they can control—a concept which we define as host-space perturbations. To some, such an observation may seem trivial. And yet, through a systematic literature review (n=316), we found that prior work applied perturbations by manipulating pre-collected datapoints (e.g., a packet captured by the router, or a network flow analysed by the ML-NIDS). Such operations, while not impossible, may be outside the reach of an attacker who can only control some (unprivileged) hosts in a network. Hence, to demonstrate how to craft host-space perturbations and study some of their effects, we experimented on well-known benchmarks and a real-world network. We show that ML-NIDS that can detect the SSH-bruteforcing attempts launched via a given command string cannot detect any attempt launched by changing a single character of such a string. We then examined how such a minuscule change in the “problem space” (i.e., the attacker's host) can lead to devastating effects on the “feature space”. We derive lessons learned on how to practically assess host-space perturbations. Our stance is that the security of ML-NIDS should be re-assessed.