# McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware

arXiv: https://arxiv.org/abs/2605.06894 · HTML: https://mlsanity.com/paper/2605.06894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 92 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 10 of 10)

- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos](https://mlsanity.com/paper/1606.06259/) (2016)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Detecting Concept Drift With Neural Network Model Uncertainty](https://mlsanity.com/paper/2107.01873/) (2021)
- [EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers](https://mlsanity.com/paper/2506.05074/) (2025)
- [Recent Advances in Malware Detection: Graph Learning and Explainability](https://mlsanity.com/paper/2502.10556/) (2025)
- [Beyond the TESSERACT:Trustworthy Dataset Curation for Sound Evaluations of Android Malware Classifiers](https://mlsanity.com/paper/2506.23814/) (2025)
- [PBP: Post-training Backdoor Purification for Malware Classifiers](https://mlsanity.com/paper/2412.03441/) (2024)
- [HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis](https://mlsanity.com/paper/2509.02113/) (2025)

## Abstract (arXiv)

Machine learning (ML) in real-world systems must contend with concept drift, adversarial actors, and a spectrum of potential features with varying costs and benefits. Malware naturally exhibits all of these complexities, but for the same reason, it is challenging to curate and organize data to study these factors. We present McNdroid, to our knowledge the largest longitudinal multimodal Android malware benchmark for malware detection and drift analysis. McNdroid spans 2013--2025, excluding 2015, and represents each application with three aligned modalities--static features from manifests and smali code, dynamic behavioral features from sandbox execution, and graph-based features from function-call graphs. Using temporally separated splits, we evaluate standard ML and deep-learning detectors across increasing train--test time gaps. Results show clear temporal degradation, while multimodal fusion outperforms the best single modality across long-term temporal gaps. Cross-modal agreement also declines over time, suggesting that drift affects both individual feature spaces and the consistency among modalities. We further analyze modality-specific drift, malware-family evolution, and temporal changes in model explanations. We publicly release McNdroid, benchmark splits, and code to support reproducible research on temporal generalization and robust multimodal learning in security-critical, non-stationary settings.