Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making

Large language models LLMs are increasingly used in cybersecurity workflows, yet it remains unclear whether they can perform structured security reasoning or merely rely on superficial cues and prior knowledge. We study this question in the context of defence selection over attack graphs derived...

Steps to TruRisk™ – 2: Measuring the Likelihood of Vulnerability Exploitation

Cybersecurity programs rely on various methods to measure the risk associated with vulnerabilities for prioritization, such as CVSS, EPSS, CISA KEV, or even internally developed systems that combine multiple approaches. While these methods help assess whether a specific vulnerability exists on an...