MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation
Not on the map. Why?
Abstract (arXiv)
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
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 33 references that are in the map. First posted on arXiv 24 May 2025.
Builds on
11 of 33 references.
References · 11
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
- 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
- 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
- 2022Test-Time Training with Masked Autoencoderscited by 212
- 2023Test-Time Training on Nearest Neighbors for Large Language Modelscited by 88
- 2020Transcending Transcend: Revisiting Malware Classification in the Presence of Concept Driftcited by 53
- 2023Test-Time Training on Video Streamscited by 37
- 2023Continuous Learning for Android Malware Detectioncited by 33
- 2024Revisiting Concept Drift in Windows Malware Detection: Adaptation to Real Drifted Malware with Minimal Samplescited by 11
- 2024MORPH: Towards Automated Concept Drift Adaptation for Malware Detectioncited by 8
- 2023Efficient Concept Drift Handling for Batch Android Malware Detection Modelscited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.