Detection of Stealthy Bitstreams in Cloud FPGAs using Graph Convolutional Networks*

FPGAs are frequently utilized in cloud computing environments for high performance computing and neural network accelerators. Furthermore, multi-tenancy allows multiple users to upload customized modules on the FPGA, while maintaining logical isolation. However, attackers can take advantage of the multi-tenant environment to launch voltage-based attacks and denial-of-service (DoS). An attacker might stealthily split power-wasting ring oscillators (ROs) across multiple windows within an FPGA configuration bitstream, making it challenging for traditional detection mechanisms to identify these dispersed components as part of a larger malicious circuit. We propose a methodology to detect these malicious bitstreams by transforming individual windows within an FPGA bitstream into a graph-based representation. Leveraging this graph structure, our method employs graph convolutional networks (GCNs) in the training phase to capture malicious patterns from the bitstreams. We use the classification accuracy, true-positive rate, and false-positive rate metrics to quantify the effectiveness of our method across diverse power-wasting circuits on multiple FPGA boards.