一句话：提出深度学习内容类型检测工具 Magika，模型仅 1MB，百万文件上平均 F1 达 99%，优于现有工具。
内容类型检测旨在识别任意字节序列所编码的数据，对操作系统、开发与逆向工程环境及安全应用至关重要。本文提出 Magika，一种 AI 驱动的内容类型检测工具，其核心是可在单 CPU 上运行、仅需 1MB 内存存储权重的深度学习模型。作者在超过 100 种内容类型、逾 100 万个文件的测试集上评估，Magika 平均 F1 达到 99%，优于现有工具。工具以 Apache 2 许可证开源，模型与训练流水线公开，并已被 Gmail、Google Drive、VirusTotal 及 Apache Tika 等采用。当前版本已支持 200 多种内容类型。
The task of content-type detection—which entails identifying the data encoded in an arbitrary byte sequence—is critical for operating systems, development, reverse engineering environments, and a variety of security applications. In this paper, we introduce Magika, a novel AI-powered content-type detection tool. Under the hood, Magika employs a deep learning model that can execute on a single CPU with just 1MB of memory to store the model's weights. We show that Magika achieves an average F1 score of 99% across over a hundred content types and a test set of more than 1M files, outperforming all existing content-type detection tools today. To foster adoption and improvements, we open source Magika under an Apache 2 license on GitHub and we make our model and training pipeline publicly available. Our tool has already seen adoption by Gmail and Google Drive for attachment scanning, by VirusTotal to aid with malware analysis, and by prominent open-source projects such as Apache Tika. While this paper focuses on the initial version, Magika continues to evolve with support for over 200 content types now available. The latest developments can be found at https://github.com/google/magika.
@inproceedings{paperbot8686,
title = {MAGIKA: AI-Powered Content-Type Detection},
author = {Yanick Fratantonio and Luca Invernizzi and Loua Farah and Kurt Thomas and Marina Zhang and Ange Albertini and Francois Galilee and Giancarlo Metitieri and Julien Cretin and Alex Petit-Bianco and David Tao and Elie Bursztein},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00158}
}