针对 DNN 和 GBDT 的后门攻击——来自保险领域的案例研究
Backdoor attacks on DNN and GBDT -- A Case Study from the insurance domain
AI总结：
本文在两个保险表格数据集上评估 GBDT 与 DNN 对后门攻击的鲁棒性，发现少量带模式样本即可在部分模型上成功植入后门。
摘要：
机器学习（ML）未来可能在许多流程中发挥重要作用，对于保险公司而言同样如此。然而，ML 模型面临被攻击和操纵的风险。本文将评估保险场景中 Gradient Boosted Decision Tree（GBDT，梯度提升决策树）模型与 Deep Neural Networks（DNN，深度神经网络）的鲁棒性。为此，研究在两个来自保险场景的不同表格数据集上训练了两个 GBDT 模型和两个 DNN。以往该领域的研究主要使用同质数据，而关于异质表格数据的见解相对较少。在这些数据集上执行的 ML 任务是索赔预测（回归）和欺诈检测（二分类）。对于后门攻击，研究制作了包含特定模式的不同样本，并将其加入训练数据。结果表明，即使只添加少量样本，这类攻击也可能非常成功。后门攻击在其中一个数据集训练的模型上效果良好，但在另一个数据集训练的模型上效果较差。在真实场景中，攻击者将不得不面对若干障碍，但由于攻击只需添加极少样本即可生效，因此应当对这一风险进行评估。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
