Embedding and Extraction of Knowledge in Tree Ensemble Classifiers

Abstract

The embedding and extraction of useful knowledge is a recent trend in machine learning applications, e.g., to supplement existing datasets that are small. Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively. This paper studies the embedding and extraction of knowledge in tree ensemble classifiers, and focuses on knowledge expressible with a generic form of Boolean formulas, e.g., robustness properties and backdoor attacks. For the embedding, it is required to be preservative(the original performance of the classifier is preserved), verifiable(the knowledge can be attested), and stealthy(the embedding cannot be easily detected). To facilitate this, we propose two novel, and effective, embedding algorithms, one of which is for black-box settings and the other for white-box settings.The embedding can be done in PTIME. Beyond the embedding, we develop an algorithm to extract the embedded knowledge, by reducing the problem to be solvable with an SMT (satisfiability modulo theories) solver. While this novel algorithm can successfully extract knowledge, the reduction leads to an NP computation. Therefore, if applying embedding as backdoor attacks and extraction as defence, our results suggest a complexity gap (P vs. NP) between the attack and defence when working with tree ensemble classifiers. We apply our algorithms toa diverse set of datasets to validate our conclusion extensively.

References in corpus (13)

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Neural Trojans
• Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
• Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
• Evasion and Hardening of Tree Ensemble Classifiers
• Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy
• Defending Neural Backdoors via Generative Distribution Modeling
• Robust Decision Trees Against Adversarial Examples
• Formal Verification of Input-Output Mappings of Tree Ensembles
• Formal Verification of Decision-Tree Ensemble Model and Detection of its Violating-input-value Ranges
• Walling up Backdoors in Intrusion Detection Systems
• A Statistical Approach to Assessing Neural Network Robustness

Cited by in corpus (2)

• BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
• Tutorials on Testing Neural Networks