Agentic SABRE: An Uncertainty-Aware Neuro-Symbolic Multi-Agent Framework for Adaptive Ransomware Detection

2026-07-05

AI Summary

This study addresses the limitations of traditional ransomware detection methods caused by concept drift, evasion tactics, and behavioral polymorphism. To overcome these challenges, the authors propose an uncertainty-aware neuro-symbolic multi-agent framework that integrates semantic and behavioral evidence for collaborative decision-making. The approach leverages Monte Carlo Dropout to quantify epistemic uncertainty and employs an interpretable thresholding mechanism to facilitate human-in-the-loop decisions. Additionally, it incorporates post-hoc explanation techniques—including gradient saliency, permutation importance, and counterfactual analysis—to enhance system auditability and trustworthiness. Evaluated on the RDset and RanSMAP datasets, the method achieves a perfect AUC of 1.0, demonstrates significantly improved robustness under weak behavioral signals, reduces false positive escalations by 4.9% at equivalent recall rates, and exhibits well-calibrated predictive uncertainty.

Abstract

Ransomware has evolved into a complex, adaptive, and fast-moving adversary category in which static signatures and monolithic classifiers fail to generalise under concept drift, evasion, and behavioural polymorphism. In this paper, we present Agentic SABRE (Semantic-Behavioural Arbitration for Ransomware Evaluation), an uncertainty-aware, neuro-symbolic, multi-agent framework for adaptive ransomware detection. SABRE fuses semantic, representation-based evidence with behavioural, time-window forensic telemetry and employs Monte Carlo Dropout inference to quantify epistemic uncertainty for each agent. We introduce a decision-layer orchestrator that performs risk- and uncertainty-aware triage using two interpretable thresholds: a risk score and an uncertainty budget. High-confidence, high-risk samples are automatically contained, while uncertain or borderline cases are escalated to human analysts, establishing a flexible computational contract between autonomous response and analyst oversight. To support auditability and trust, SABRE integrates post-hoc explainability mechanisms, including gradient saliency, permutation importance, and counterfactual analysis, enabling both local and global interpretation of agent decisions. Extensive evaluation on RDset and RanSMAP demonstrates that Agentic SABRE preserves perfect discrimination on saturated semantic datasets, with AUC equal to 1.0, while improving robustness under weak behavioural signals. It achieves up to a 4.9 percent relative reduction in false escalations at equal recall while maintaining calibrated predictive uncertainty. Counterfactual analysis further shows that semantic and behavioural decisions can be reversed with bounded perturbation cost, indicating stable and interpretable decision boundaries.

Problem

• ransomware detection
• concept drift
• evasion
• behavioural polymorphism
• adaptive adversary

Innovation

• neuro-symbolic
• multi-agent
• uncertainty quantification
• adaptive ransomware detection
• explainable AI