Anomaly detection is a problem with roots dating back over 30 years. The NSL-KDD dataset has become the convention for testing and comparing new or improved models in this domain. In the field of network intrusion detection, the UNSW-NB15 dataset has recently gained significant attention over the NSL-KDD because it contains more modern attacks. In the present paper, we outline two cutting-edge architectures that push the boundaries of model accuracy for these datasets, both framed in the context of anomaly detection and intrusion classification. We summarize training methodologies, hyperparameters, regularization, and other aspects of model architecture. Moreover, we also utilize the standard deviation of weight values to design a new regularization technique. Then, we embed it on both models and report the models’ performance. Finally, we detail potential improvements aimed at increasing models’ accuracy.

中文翻译：

---

基于新正则化的深度自动编码器和前馈网络用于异常检测

异常检测是根源可以追溯到30年前的问题。NSL-KDD数据集已成为在该领域中测试和比较新模型或改进模型的惯例。在网络入侵检测领域，UNSW-NB15数据集由于包含更先进的攻击而最近在NSL-KDD上引起了广泛关注。在本文中，我们概述了两种最先进的体系结构，它们推动了这些数据集的模型精度边界，两者都在异常检测和入侵分类的背景下进行了框架化。我们总结了训练方法，超参数，正则化和模型架构的其他方面。此外，我们还利用权重值的标准偏差来设计新的正则化技术。然后，我们将其嵌入两个模型中并报告模型的性能。最后，