@inproceedings{a4ce42e20e4645f78e1864502754eaa8,
title = "Decoding HDF5: Machine Learning File Forensics and Data Injection",
abstract = "The prevalence of ML in computing is rapidly expanding and Machine Learning (ML) systems are continuously applied to novel challenges. As the adoption of these systems grows, their security becomes increasingly important. Any security vulnerabilities within an ML system can jeopardize the integrity of dependent and related systems. Modern ML systems commonly encapsulate trained models in a compact format for storage and distribution, including TensorFlow 2 (TF2) and its utilization of the Hierarchical Data Format 5 (HDF5) file format. This work explores into the security implications of TF2 {\textquoteright}s use of the HDF5 format to save trained models, aiming to uncover potential weaknesses via forensic analysis. Specifically, we investigate the injection and detection of foreign data in these packaged files using a custom tool external to TF2, leading to the development of a dedicated forensic analysis tool for TF2 {\textquoteright}s HDF5 model files.",
keywords = "File Forensics, HDF5, Machine Learning, TensorFlow 2",
author = "Clinton Walker and Ibrahim Baggili and Hao Wang",
note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.; 14th EAI International Conference on Digital Forensics and Cyber Crime, ICDF2C 2023 ; Conference date: 30-11-2023 Through 30-11-2023",
year = "2024",
doi = "10.1007/978-3-031-56580-9\_12",
language = "English",
isbn = "9783031565793",
series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",
pages = "193--211",
editor = "Sanjay Goel and \{Nunes de Souza\}, \{Paulo Roberto\}",
booktitle = "Digital Forensics and Cyber Crime - 14th EAI International Conference, ICDF2C 2023, Proceedings",
}