Most TinyML hardware accelerators focus on supporting Quantized Neural Networks (QNNs) to meet stringent constraints on power consumption and size. Despite this, the security aspects of quantization within TinyML hardware remain largely unexplored. Although previous studies indicate that QNNs demonstrate similar or enhanced robustness when compared to full-precision Deep Neural Networks (DNNs) against typical evasion attacks, no attack strategies tailored specifically for TinyML hardware have been proposed yet. This paper addresses this shortfall by demonstrating how a two-step attack pipeline can surpass the current state-of-the-art in the QNN context and shows the need for more hardware-aware security research.

翻译：大多数TinyML硬件加速器专注于支持量化神经网络（QNN），以满足严格的功耗和尺寸限制。尽管如此，TinyML硬件中量化的安全问题仍未得到充分探索。尽管先前研究表明，与全精度深度神经网络（DNN）相比，QNN在应对典型规避攻击时表现出相似或更强的鲁棒性，但目前尚未提出专门针对TinyML硬件的攻击策略。本文通过展示一种两步攻击管道如何超越QNN领域当前最先进水平，弥补了这一不足，并揭示了开展更多硬件感知安全研究的必要性。