PassRecover: A Multi-FPGA System for End-to-End Offline Password Recovery Acceleration

• DOI: 10.3390/electronics14071415
• Publication Date: 2025-04-01T09:29:19Z
• Authors: Guangwei Xie; Xitian Fan; Zhongchen Huang; Wei Cao; Fan Zhang

In the domain of password recovery, deep learning has emerged as a pivotal technology for enhancing recovery efficiency. Despite its effectiveness, inherent computation complexity learning-based generation algorithms poses substantial challenges, particularly in achieving synergistic acceleration between inference, and plaintext encryption process. this paper, we introduce PassRecover, multi-FPGA-based computing system that can simultaneously accelerate learning-driven an end-to-end manner. The architecture incorporates neural processing unit (NPU) array configured to operate under streaming dataflow paradigm parallel processing. It is first approach explore benefit offline recovery. For comprehensive evaluation, PassRecover benchmarked against PassGAN five industry-standard (Office2010, Office2013, PDF1.7, Winzip, RAR5). Experimental results demonstrate excellent performance: Compared latest work only algorithms, achieves average 101.5% speedup across all tested algorithms. When compared graphics (GPU)-based implementations, delivers 93.01% faster speeds 3.73× superior energy These establish promising solution resource-constrained scenarios requiring high throughput