Abstract
Decision tree is one of the simplest, yet popular, machine learning algorithms. It has a very long history of research and application, and has many variants. This chapter will present a training algorithm for decision trees and discuss several algorithms to identify the safety and security risks of a trained decision tree or its training algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A more generic form is f 2 ∈ (b 2 − 𝜖 l, b 2 + 𝜖 u], where both 𝜖 l and 𝜖 u are small numbers that together represents a concise piece of knowledge on feature f 2, i.e., a small range of values around f 2 = b 2. For brevity, we only illustrate the simplified case where 𝜖 l = 𝜖 u = 𝜖.
References
Wei Huang, Youcheng Sun, Xingyu Zhao, James Sharp, Wenjie Ruan, Jie Meng, and Xiaowei Huang. Coverage-guided testing for recurrent neural networks. IEEE Transactions on Reliability, pages 1–16, 2021.
Wei Huang, Xingyu Zhao, and Xiaowei Huang. Embedding and extraction of knowledge in tree ensemble classifiers. Machine Learning, 2021.
Laurent Hyafil and Ronald L. Rivest. Constructing optimal binary decision trees is np-complete. Information Processing Letters, 5(1):15–17, 1976.
Alex Kantchelian, J. D. Tygar, and Anthony D. Joseph. Evasion and hardening of tree ensemble classifiers. In Proceedings of the 33nd International Conference on Machine Learning, volume 48, pages 2387–2396, 2016.
Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. Stealing machine learning models via prediction apis. In Proceedings of the 25th USENIX Conference on Security Symposium, SEC’16, page 601–618, USA, 2016. USENIX Association.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Huang, X., Jin, G., Ruan, W. (2023). Decision Tree. In: Machine Learning Safety. Artificial Intelligence: Foundations, Theory, and Algorithms. Springer, Singapore. https://doi.org/10.1007/978-981-19-6814-3_5
Download citation
DOI: https://doi.org/10.1007/978-981-19-6814-3_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6813-6
Online ISBN: 978-981-19-6814-3
eBook Packages: Computer ScienceComputer Science (R0)