HYDRA: Proactive Android Malware Drift Adaptation via Hierarchical Graph Contrastive Learning
HYDRA uses hierarchical Android app graphs and contrastive learning to adapt malware detectors to concept drift with far fewer labels.
Researchers propose HYDRA, a proactive framework that models Android apps with control-flow and function-call graphs and aligns historical and new data through cross-domain contrastive learning. Pseudo-labels for unlabeled target samples pull similar applications together without adversarial training. On large time-ordered malware datasets, HYDRA reports lower false-negative and false-positive rates than baselines while using up to 87.5% fewer labeled samples.
- Combines control-flow and function-call graphs into one app model.
- Contrastive learning aligns historical and new malware distributions.
- Pseudo-labels replace unstable adversarial domain training.
- Reports up to 87.5% fewer labeled samples than baselines.
Full article205 words · extracted from arxiv.org · click to collapse
Concept drift, driven by the rapid evolution of Android malware, severely degrades the performance of machine learning detectors. Current adaptation strategies are often reactive, responding only after performance has dropped and imposing a significant manual annotation burden, or they are proactive but rely on unstable adversarial training and incomplete, single-level graph representations. To overcome these limitations, we propose HYDRA (Hybrid Drift Adaptation), a proactive adaptation framework that learns drift-invariant representations from hierarchically structured data. HYDRA first models applications using a hybrid graph structure, combining fine-grained Control Flow Graphs (CFGs) and coarse-grained Function Call Graphs (FCGs) to capture comprehensive behavioral patterns. It then introduces a novel cross-domain contrastive learning objective that aligns historical (source) and new (target) data distributions. By generating pseudo-labels for unlabeled target samples, our method pulls representations of semantically similar applications together, regardless of their domain, within a single, stable optimization process. This approach unifies feature learning and domain alignment, eliminating the need for complex adversarial objectives. Extensive experiments on large-scale, time-ordered malware datasets demonstrate that HYDRA achieves substantially lower False Negative and False Positive Rates than state-of-the-art baselines while requiring up to 87.5% fewer labeled samples. Our work thus offers a robust and efficient solution to combat concept drift in security applications.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.26352