ADAD: An Energy-Efficient Hardware Solution for Real-Time Anomaly Detection Using Extended Decorrelation-Based Method

Abstract

This paper presents ADAD, an energy-efficient hardware solution for real-time streaming anomaly detection built on an extended decorrelation-based algorithm (EDAD). EDAD extends a prior decorrelation-based anomaly detector, which operates in a continual-updating regime suited for nonstationary environments, with a Freeze-After-Learn regime for stationary environments where only background data is available. EDAD yield a unified algorithm covering both stationary and non-stationary environments while operating strictly samplewise, making it well suited for streaming deployment. Application agnosticism is validated across two different benchmarks. On the LHC physics dataset, EDAD outperforms two autoencoderbased baselines on three of four detection tasks. On nine widelyused ODDS benchmark datasets spanning healthcare, image, astronautics, and linguistics domains, EDAD achieves the highest average AUC of 0.879 among four established detectors. ADAD realizes both EDAD regimes in a unified scalable architecture, supporting up to 512 feature dimensions. FPGA-based ADAD implementation delivers substantial energy efficiency gains over general-purpose platforms, up to 1587× over CPU and 3514× over GPU. It also achieves $\mathbf{1. 8} \times$ lower energy per sample and higher AUC versus prior FPGA-based anomaly detectors. The 45 nm ASIC implementation achieves pico-joule per operation across feature dimensions, offering a practical applicationagnostic solution for energy-efficient edge AD and system-level integration.