Name2Pkg: Lightweight One-Class Android Malware Screening via Name-Package Correspondence Modeling
Name2Pkg flags Android malware from app-name and package-name mismatch, with ROC-AUC 0.982.
Name2Pkg is a one-class Android malware screener that uses only the user-facing app name and the package name, avoiding costly APK or runtime features. A character-level sequence model estimates how likely a package name is given the app name and is trained and thresholded on benign data alone. On 67,129 real-world applications it reached ROC-AUC 0.982 and malware recall 0.885 at a false-positive rate of 0.044. The 3.57 MiB model infers in 28.20 ms per sample on CPU and is proposed as a pre-filter for large-scale screening.
- Uses only app name and package name, not APK internals.
- ROC-AUC 0.982 and malware recall 0.885 at a 4.4% false-positive rate.
- Trained only on benign data from 67,129 real-world applications.
- Checkpoint is 3.57 MiB, with 28.20 ms CPU inference per sample.
Full article188 words · extracted from arxiv.org · click to collapse
Deep learning-based malware detection has been widely adopted in security-critical services. Most detection methods rely on internal features extracted from APK files or runtime behavior. However, extracting these features is computationally expensive. This limits their use in large-scale, early-stage screening. Malicious apps may exhibit weak correspondence between their user-facing app names and package names, providing a low-cost screening signal. We present Name2Pkg, a lightweight one-class classification method. It leverages only the app name and the package name. We formulate malware screening as a sequence anomaly detection problem. A character-level sequence-to-sequence model estimates the conditional likelihood of a package name given the app name. The length-normalized negative log-likelihood serves as the anomaly score. We train the model and calibrate the threshold using only benign data. Using a dataset of 67,129 real-world applications, Name2Pkg achieves an area under the receiver operating characteristic curve (ROC-AUC) of 0.982 and malware recall of 0.885 at an achieved false-positive rate of 0.044 on held-out test data. It has a 3.57 MiB checkpoint and a CPU inference latency of 28.20 ms per sample. Name2Pkg provides an efficient and effective pre-filtering signal for large-scale security systems.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.24389