Backdoor attacks on DNN and GBDT -- A Case Study from the insurance domain

Abstract

Machine learning (ML) will likely play a large role in many processes in the future, also for insurance companies. However, ML models are at risk of being attacked and manipulated. In this work, the robustness of Gradient Boosted Decision Tree (GBDT) models and Deep Neural Networks (DNN) within an insurance context will be evaluated. Therefore, two GBDT models and two DNNs are trained on two different tabular datasets from an insurance context. Past research in this domain mainly used homogenous data and there are comparably few insights regarding heterogenous tabular data. The ML tasks performed on the datasets are claim prediction (regression) and fraud detection (binary classification). For the backdoor attacks different samples containing a specific pattern were crafted and added to the training data. It is shown, that this type of attack can be highly successful, even with a few added samples. The backdoor attacks worked well on the models trained on one dataset but poorly on the models trained on the other. In real-world scenarios the attacker will have to face several obstacles but as attacks can work with very few added samples this risk should be evaluated.

40 pages, 14 figures

References in corpus (7)

• SMOTE: Synthetic Minority Over-sampling Technique
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Deep Neural Networks and Tabular Data: A Survey
• Insights into Performance Fitness and Error Metrics for Machine Learning
• Adversarial Examples: Opportunities and Challenges
• Ransomware Classification and Detection With Machine Learning Algorithms
• Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models