论文标题
可转移且自动调整深度加固学习，以进行具有成本效益的网络钓鱼检测
A Transferable and Automatic Tuning of Deep Reinforcement Learning for Cost Effective Phishing Detection
论文作者
论文摘要
许多具有挑战性的现实世界问题需要部署合奏多个互补学习模型，以达到可接受的绩效水平。虽然有效，但将整个合奏应用于每个样本都是昂贵且通常不必要的。深钢筋学习（DRL）提供了一种具有成本效益的替代方案，其中探测器是根据其前辈的输出动态选择的，其实用性与计算成本相比加权。尽管它们具有潜力，但基于DRL的解决方案并未在这种能力上广泛使用，部分原因是在为每个新任务配置奖励功能，DRL代理对数据变化的不可预测的反应以及无法使用常见性能指标（例如TPR/FPR）指导AlgorithM的性能。在这项研究中，我们提出了微调和校准基于DRL的策略的方法，以便它们可以满足多个绩效目标。此外，我们提出了一种将有效的安全策略从一个数据集传输到另一个数据集的方法。最后，我们证明我们的方法对对抗性攻击非常强大。
Many challenging real-world problems require the deployment of ensembles multiple complementary learning models to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often unnecessary. Deep Reinforcement Learning (DRL) offers a cost-effective alternative, where detectors are dynamically chosen based on the output of their predecessors, with their usefulness weighted against their computational cost. Despite their potential, DRL-based solutions are not widely used in this capacity, partly due to the difficulties in configuring the reward function for each new task, the unpredictable reactions of the DRL agent to changes in the data, and the inability to use common performance metrics (e.g., TPR/FPR) to guide the algorithm's performance. In this study we propose methods for fine-tuning and calibrating DRL-based policies so that they can meet multiple performance goals. Moreover, we present a method for transferring effective security policies from one dataset to another. Finally, we demonstrate that our approach is highly robust against adversarial attacks.
