An Empirical Study of Artifacts and Security Risks in the Pre-trained Model Supply Chain
Authors:
Open Access
- 8 November 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 105-114
Abstract
Deep neural networks achieve state-of-the-art performance on many tasks, but require increasingly complex architectures and costly training procedures. Engineers can reduce costs by reusing a pre-trained model (PTM) and fine-tuning it for their own tasks. To facilitate software reuse, engineers collaborate around model hubs, collections of PTMs and datasets organized by problem domain. Although model hubs are now comparable in popularity and size to other software ecosystems, the associated PTM supply chain has not yet been examined from a software engineering perspective. We present an empirical study of artifacts and security features in 8 model hubs. We indicate the potential threat models and show that the existing defenses are insufficient for ensuring the security of PTMs. We compare PTM and traditional supply chains, and propose directions for further measurements and tools to increase the reliability of the PTM supply chain.Keywords
Funding Information
- Cisco
- NSF (National Science Foundation) (2107230, 2229703, 2107020, 2104319)
This publication has 30 references indexed in Scilit:
- Backdoor Attacks Against Transfer Learning With Pre-Trained Deep Learning ModelsIEEE Transactions on Services Computing, 2020
- On testing machine learning programsJournal of Systems and Software, 2020
- Deep learning-based image recognition for autonomous drivingIATSS Research, 2019
- An Empirical Study Towards Characterizing Deep Learning Development and Deployment Across Different Frameworks and Platforms2019
- The impact of regular expression denial of service (ReDoS) in practice: an empirical study at the ecosystem scale2018
- On the impact of security vulnerabilities in the npm package dependency network2018
- Threat of Adversarial Attacks on Deep Learning in Computer Vision: A SurveyIEEE Access, 2018
- Generative Adversarial Networks: An OverviewIEEE Signal Processing Magazine, 2018
- DeepLog2017
- Software ecosystems – A systematic literature reviewJournal of Systems and Software, 2013