MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation

2025/05/24 by Eunjin Roh, Roh, Eunjin, Yiğitcan Kaya +7 · 1 citation
Computer Science · #Advanced Malware Detection Techniques #Cryptography and Security (cs.CR) #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.2505.18734

openalex publication_date 2025/05/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present MADCAT, a self-supervised approach designed to address the concept drift problem in malware detection. MADCAT employs an encoder-decoder architecture and works by test-time training of the encoder on a small, balanced subset of the test-time data using a self-supervised objective. During test-time training, the model learns features that are useful for detecting both previously seen (old) data and newly arriving samples. We demonstrate the effectiveness of MADCAT in continuous Android malware detection settings. MADCAT consistently outperforms baseline methods in detection performance at test time. We also show the synergy between MADCAT and prior approaches in addressing concept drift in malware detection

Citations

• Revisiting Concept Drift in Windows Malware Detection: Adaptation to Real Drifted Malware with Minimal Samples
• MORPH: Towards Automated Concept Drift Adaptation for Malware Detection
• Efficient Concept Drift Handling for Batch Android Malware Detection Models
• Test-Time Training on Video Streams
• Test-Time Training on Nearest Neighbors for Large Language Models
• A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts
• Continuous Learning for Android Malware Detection
• Test-Time Training with Masked Autoencoders
• Masked Autoencoders Are Scalable Vision Learners
• Transcending Transcend: Revisiting Malware Classification in the\n Presence of Concept Drift
• Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
• A unifying view on dataset shift in classification

Cited by

• Concept Drift Adaptation Using Self-Supervised and Reinforcement Learning In Android Malware Detection

Related

• MORPH: Towards Automated Concept Drift Adaptation for Malware Detection
• ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection
• Efficient Concept Drift Handling for Batch Android Malware Detection Models
• LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis
• DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift