Decoding HDF5: Machine Learning File Forensics and Data Injection

Clinton Walker, Ibrahim Baggili, Hao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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 ’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 ’s HDF5 model files.

Original languageEnglish
Title of host publicationDigital Forensics and Cyber Crime - 14th EAI International Conference, ICDF2C 2023, Proceedings
EditorsSanjay Goel, Paulo Roberto Nunes de Souza
Pages193-211
Number of pages19
DOIs
StatePublished - 2024
Event14th EAI International Conference on Digital Forensics and Cyber Crime, ICDF2C 2023 - New York, United States
Duration: 30 Nov 202330 Nov 2023

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume570 LNICST
ISSN (Print)1867-8211
ISSN (Electronic)1867-822X

Conference

Conference14th EAI International Conference on Digital Forensics and Cyber Crime, ICDF2C 2023
Country/TerritoryUnited States
CityNew York
Period30/11/2330/11/23

Keywords

  • File Forensics
  • HDF5
  • Machine Learning
  • TensorFlow 2

Fingerprint

Dive into the research topics of 'Decoding HDF5: Machine Learning File Forensics and Data Injection'. Together they form a unique fingerprint.

Cite this