We explore the capabilities of Large Language Models (LLMs) to assist or substitute devices (i.e., firewalls) and humans (i.e., security experts) respectively in the detection and analysis of security incidents. We leverage transformer-based technologies, from relatively small to foundational sizes, to address the problem of correctly identifying the attack severity (and accessorily identifying and explaining the attack type). We contrast a broad range of LLM techniques (prompting, retrieval augmented generation, and fine-tuning of several models) using state-of-the-art machine learning models as a baseline. Using proprietary data from commercial deployment, our study provides an unbiased picture of the strengths and weaknesses of LLM for intrusion detection.
Failure prediction is a key component of modern autonomic systems. A crucial decision to take when performing it is which observation window to use, this is, to decide the time period in the past that will be taken into account in order to accurately predict. Currently, this decision is a highly manual process, dependent on expert knowledge. To alleviate this problem, we propose the usage of a customized genetic algorithm alongside a machine learning technique, random forests, which optimizes a novel, multiple observation window schemes that allows for more modeling complexity than other schemes present on the literature. We validate it using ten different events extracted from two real, industrial data sets: one from a high performance computing environment and one from a computer network. We show that our algorithm creates models that optimize performance while reducing the observed time automatically with minimal user input required.
Troubleshooting WiFi networks is knowingly difficult due to the variability of the wireless medium. Complementary to existing works that focus on detecting short-term fluctuations of radio signals (i.e., anomalies), we tackle the problem of reliably detecting long-term changes in statistical properties of WiFi networks. We propose a new method to reliably gain insights on such environmental changes, which we refer to as Random Access Point Forest (RAPF). RAPF identifies the changes from a forest of individual learners, each of them consisting of a random tree approximating the signal of a specific pair of APs. The biased selection of APs in a distributed manner along with the stochastic construction of each individual tree ensure its robustness to noise and biases. We conduct a measurement campaign on a real WLAN by collecting the path loss among pairs of APs in a network for which labels are available and perform an extensive comparison of our methodology against state-of-the-art change point methodologies, which conclusively shows RAPF to yield the most robust detection capabilities.