Hybrid deep learning improves malware detection with limited data
A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
Cryptography and SecurityArtificial IntelligenceMachine Learning
Summary
Cyber attacks like ransomware lock up important files and demand payment to unlock them, causing big problems. Detecting new or rare malware is tough because there isn’t much data to learn from. The authors created a combined system that first simplifies the malware data to its key features, then uses a special learning method that can quickly adapt to new malware types even with few examples. Their tests show this method detects malware well even when only a small number of samples are available. This approach could help protect critical places like hospitals and factories from cyberattacks.
What this means in practice
- •For cybersecurity teams: Detect new ransomware variants early with a model that learns from very few labeled examples.
- •For industrial control teams: Protect critical manufacturing infrastructure by identifying malware threats quickly despite scarce attack data.
Tested on one dataset.
Authors
Emmanuela Andam, Yasir Abbas Zaidi, Abdelali Hadir, Emmanuel Grant, Naima Kaabouch
Abstract
Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are typically launched through phishing emails, malicious downloads, or exploitation of software vulnerabilities to gain system access. Once inside, the malware encrypts files and demands a ransom, often in cryptocurrency, for the decryption key. Conventional detection methods often struggle with novel or scarce samples, leaving systems vulnerable. To address these challenges, this paper proposes a hybrid deep learning framework that combines an Autoencoder Feature Extractor (AFE) with a Model Agnostic Meta Learning (MAML) classifier for few shot malware detection. The AFE generates compact latent features that reduce noise and dimensionality, while the MAML classifier rapidly adapts to new threats using limited labeled data. Experiments conducted on the Ransomware Dataset 2024 demonstrate the effectiveness of the framework in binary classification tasks. Across one to fifty shot settings, the proposed model consistently achieves high accuracy, F1 score, and Matthews Correlation Coefficient values, maintaining reliable classification even under extreme scarcity. These results highlight the model's robustness and effectiveness in adapting to limited data scenarios, demonstrating the potential of combining feature extraction with meta learning to enhance resilience against malware, particularly in sectors such as healthcare, manufacturing, and public infrastructure, where cyberattacks can cause significant operational and financial disruption.