PDNSig: Identifying Multi-Tenant Cloud FPGAs with Power Distribution Network-Based Signatures
Huifeng Zhu, Weidong Cao, Xuan Zhang · 2023
The increasing use of Field Programmable Gate Arrays (FPGAs) in modern cloud data centers, such as Amazon's EC2 F1 instances, has led to a rising concern regarding remote side-channel attacks, which necessitates thorough investigation and analysis. Existing threat models crucially depend on a critical assumption: attackers could uniquely identify the target FPGA chip (or the specific die in a chip). However, this assumption is impractical in real cloud scenarios since security measures routinely implemented by cloud FPGA providers can anonymize the devices. To address this critical limitation, we propose PDNSig-a power distribution network (PDN)-based signature generation framework. By recognizing the complexity and irregularity of the PDN network and its susceptibility to process variation, we reveal that the impedance profile of an FPGA's PDN can uniquely distinguish different FPGAs. Particularly, we inject pseudo-random noises into the PDN by turning on or off power-hungry circuits (e.g., ring oscillators). The corresponding response of PDN is subsequently captured by on-chip sensors (e.g., time-to-digital converter), followed by a statistical analysis to obtain the PDN impedance at different frequencies. This proposed novel random process-based PDN measurement methodology can be directly applied to prior attack infrastructures with low hardware overhead. We perform thorough characterizations and demonstrate the effectiveness of PDNSig by conducting multiple real-world experiments on 40 Amazon cloud FPGA chips (including 120 dies). Experimental results show that the extracted PDN-based signatures can distinguish all 40 chips reliably. Additionally, a 99% true positive rate and 0.4% false positive rate are also achieved when identifying the 120 distinctive dies associated with these FPGA chips.