With the advent of globalization, hardware trojans provide an ever-present threat to the security of devices. Much of the research to date has centered around documenting and providing detection methods for digital trojans. Few, however, have explored the space of trojans in the RF/analog front end. Two hardware trojans, an analytical analysis of the trojan impacts on two different types of amplifiers, and an unsupervised ML detection method for edge IOT applications using magnetic tunnel junction sensors for side-channel monitoring are explored. A classification autoencoder for anomaly detection is presented with an accuracy of greater than 90% with both single tone and BLE data is presented.

中文翻译：

---

通过电磁侧通道检测射频模拟硬件木马

随着全球化的到来，硬件木马对设备的安全性构成了永远存在的威胁。迄今为止，大部分研究都集中在记录和提供数字木马的检测方法。然而，很少有人探索射频/模拟前端中的特洛伊木马空间。探索了两个硬件木马、木马对两种不同类型放大器的影响的分析分析，以及使用磁性隧道结传感器进行边信道监测的边缘物联网应用的无监督机器学习检测方法。提出了一种用于异常检测的分类自动编码器，其单音和 BLE 数据的准确率均大于 90%。