TY - GEN
T1 - Decoding HDF5
T2 - 14th EAI International Conference on Digital Forensics and Cyber Crime, ICDF2C 2023
AU - Walker, Clinton
AU - Baggili, Ibrahim
AU - Wang, Hao
N1 - Publisher Copyright:
© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - File Forensics
KW - HDF5
KW - Machine Learning
KW - TensorFlow 2
UR - http://www.scopus.com/inward/record.url?scp=85190427582&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85190427582&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-56580-9_12
DO - 10.1007/978-3-031-56580-9_12
M3 - Conference contribution
AN - SCOPUS:85190427582
SN - 9783031565793
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
SP - 193
EP - 211
BT - Digital Forensics and Cyber Crime - 14th EAI International Conference, ICDF2C 2023, Proceedings
A2 - Goel, Sanjay
A2 - Nunes de Souza, Paulo Roberto
Y2 - 30 November 2023 through 30 November 2023
ER -