Cascade Watchdog：一种用于离群点检测的多层对抗防护机制
Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection
AI总结：
针对神经网络分布外检测受可用数据限制的问题，提出基于GAN生成数据的多层级联看门狗机制，通过对抗训练扩充难检测样本的相似数据并增设二级防护，显著提升了难样本检测效果且保持极低假阳性率。
摘要：
分布外内容的识别对神经网络的成功部署至关重要。目前已开发出看门狗技术来支持这类输入的检测，但可用数据量会限制其性能。生成对抗网络已展现出诸多能力，包括生成精度极高的仿本的能力。本文提出并通过实验评估了一种多层看门狗模型，该模型利用GAN（生成对抗网络）生成的数据构建，用于提升分布外检测效果。级联看门狗采用对抗训练来增加与更难检测的分布外元素相似的可用数据量，随后按顺序添加一个专门的二级防护层。结果表明，该方法在检测最具挑战性的分布外输入方面实现了稳定且显著的提升，同时保持了极低的假阳性率。
英文摘要：
The identification of out-of-distribution content is critical to the successful implementation of neural networks. Watchdog techniques have been developed to support the detection of these inputs, but the performance can be limited by the amount of available data. Generative adversarial networks have displayed numerous capabilities, including the ability to generate facsimiles with excellent accuracy. This paper presents and empirically evaluates a multi-tiered watchdog, which is developed using GAN generated data, for improved out-of-distribution detection. The cascade watchdog uses adversarial training to increase the amount of available data similar to the out-of-distribution elements that are more difficult to detect. Then, a specialized second guard is added in sequential order. The results show a solid and significant improvement on the detection of the most challenging out-of-distribution inputs while preserving an extremely low false positive rate.
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。
