Adaptive alert prioritisation in security operations centres via learning to defer with human feedback

TL;DR

This paper introduces an adaptive alert prioritisation framework for security operations centres that uses deep reinforcement learning from human feedback to improve decision-making, reduce false positives, and lessen analyst workload.

Contribution

It proposes L2DHF, a novel adaptive learning framework that dynamically incorporates human feedback to optimize alert deferral decisions in SOCs, outperforming static models.

Findings

L2DHF achieves 13-16% higher accuracy on UNSW-NB15.

L2DHF achieves 60-67% higher accuracy on CICIDS2017.

L2DHF reduces high-category alert misprioritisation by 98%.

Abstract

Alert prioritisation (AP) is crucial for security operations centres (SOCs) to manage the overwhelming volume of alerts and ensure timely detection and response to genuine threats, while minimising alert fatigue. Although predictive AI can process large alert volumes and identify known patterns, it struggles with novel and evolving scenarios that demand contextual understanding and nuanced judgement. A promising solution is Human-AI teaming (HAT), which combines human expertise with AI's computational capabilities. Learning to Defer (L2D) operationalises HAT by enabling AI to "defer" uncertain or unfamiliar cases to human experts. However, traditional L2D models rely on static deferral policies that do not evolve with experience, limiting their ability to learn from human feedback and adapt over time. To overcome this, we introduce Learning to Defer with Human Feedback (L2DHF), an adaptive deferral framework that leverages Deep Reinforcement Learning from Human Feedback (DRLHF) to optimise deferral decisions. By dynamically incorporating human feedback, L2DHF continuously improves AP accuracy and reduces unnecessary deferrals, enhancing SOC effectiveness and easing analyst workload. Experiments on two widely used benchmark datasets, UNSW-NB15 and CICIDS2017, demonstrate that L2DHF significantly outperforms baseline models. Notably, it achieves 13-16% higher AP accuracy for critical alerts on UNSW-NB15 and 60-67% on CICIDS2017. It also reduces misprioritisations, for example, by 98% for high-category alerts on CICIDS2017. Moreover, L2DHF decreases deferrals, for example, by 37% on UNSW-NB15, directly reducing analyst workload. These gains are achieved with efficient execution, underscoring L2DHF's practicality for real-world SOC deployment.