TL-RL-FusionNet: An Adaptive and Efficient Reinforcement Learning-Driven Transfer Learning Framework for Detecting Evolving Ransomware Threats

TL;DR

TL-RL-FusionNet is an adaptive reinforcement learning framework that enhances ransomware detection by dynamically reweighting samples and leveraging transfer learning with efficient feature extraction.

Contribution

It introduces a novel RL-guided hybrid model combining transfer learning backbones with a lightweight classifier for evolving ransomware detection.

Findings

Achieves 99.1% accuracy and 98.6% precision on a balanced dataset.

Outperforms non-RL baselines by up to 2.5% in accuracy.

Reduces training time by 55% and RAM usage by 59%.

Abstract

Modern ransomware exhibits polymorphic and evasive behaviors by frequently modifying execution patterns to evade detection. This dynamic nature disrupts feature spaces and limits the effectiveness of static or predefined models. To address this challenge, we propose TL-RL-FusionNet, a reinforcement learning (RL)-guided hybrid framework that integrates frozen dual transfer learning (TL) backbones as feature extractors with a lightweight residual multilayer perceptron (MLP) classifier. The RL agent supervises training by adaptively reweighting samples in response to variations in observable ransomware behavior. Through reward and penalty signals, the agent prioritizes complex cases such as stealthy or polymorphic ransomware employing obfuscation, while down-weighting trivial samples including benign applications with simple file I/O operations or easily classified ransomware. This adaptive mechanism enables the model to dynamically refine its strategy, improving resilience against evolving threats while maintaining strong classification performance. The framework utilizes dynamic behavioral features such as file system activity, registry changes, network traffic, API calls, and anti-analysis checks, extracted from sandbox-generated JSON reports. These features are transformed into RGB images and processed using frozen EfficientNetB0 and InceptionV3 models to capture rich feature representations efficiently. Final classification is performed by a lightweight residual MLP guided by an RL (Q-learning) agent. Experiments on a balanced dataset of 1,000 samples (500 ransomware, 500 benign) show that TL-RL-FusionNet achieves 99.1% accuracy, 98.6% precision, 99.6% recall, and 99.74% AUC, outperforming non-RL baselines by up to 2.5% in accuracy and 3.1% in recall. Efficiency analysis shows 55% lower training time and 59% reduced RAM usage, demonstrating suitability for real-world deployment.