Benchmarking the Energy Cost of Assurance in Neuromorphic Edge Robotics
It addresses the problem of sustainable and high-assurance AI for edge robotics, particularly in power-constrained environments like cislunar space, with incremental improvements in defense efficiency.
This paper tackles the trade-off between robustness and energy efficiency in edge robotics by quantifying the energy cost of adversarial defense in neuromorphic systems, showing that the Hierarchical Temporal Defense framework reduces adversarial success rates significantly (e.g., from 82.1% to 18.7%) while maintaining low energy consumption of about 45 microjoules per inference.
Deploying trustworthy artificial intelligence on edge robotics imposes a difficult trade-off between high-assurance robustness and energy sustainability. Traditional defense mechanisms against adversarial attacks typically incur significant computational overhead, threatening the viability of power-constrained platforms in environments such as cislunar space. This paper quantifies the energy cost of assurance in event-driven neuromorphic systems. We benchmark the Hierarchical Temporal Defense (HTD) framework on the BrainChip Akida AKD1000 processor against a suite of adversarial temporal attacks. We demonstrate that unlike traditional deep learning defenses which often degrade efficiency significantly with increased robustness, the event-driven nature of the proposed architecture achieves a superior trade-off. The system reduces gradient-based adversarial success rates from 82.1% to 18.7% and temporal jitter success rates from 75.8% to 25.1%, while maintaining an energy consumption of approximately 45 microjoules per inference. We report a counter-intuitive reduction in dynamic power consumption in the fully defended configuration, attributed to volatility-gated plasticity mechanisms that induce higher network sparsity. These results provide empirical evidence that neuromorphic sparsity enables sustainable and high-assurance edge autonomy.