EREBA: Black-box Energy Testing of Adaptive Neural Networks
EREBA: Black-box Energy Testing of Adaptive Neural Networks
复制标题
DOI：
10.1145/3510003.3510088
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Mirazul Haque;Yaswanth Yadlapalli;Wei Yang;Cong Liu
中科院分区：
文献类型：
--
作者：
Mirazul Haque;Yaswanth Yadlapalli;Wei Yang;Cong Liu
最近，针对诸如具有严格能量约束的嵌入式系统等环境，提出了各种深度神经网络（DNN）模型。与基于准确性的鲁棒性相比，确定 DNN 相对于其能量消耗的鲁棒性（能量鲁棒性）的基本问题相对尚未被探索。这项工作研究了自适应神经网络 (AdNN) 的能量鲁棒性，这是一种针对许多能源敏感领域提出的节能 DNN，最近受到关注。我们提出了 EREBA，这是第一个用于确定 AdNN 能量鲁棒性的黑盒测试方法。 EREBA 探索并推断 AdNN 的输入与能量消耗之间的关系，以生成能量澎湃的样本。使用三个最先进的 AdNN 进行的广泛实施和评估表明，EREBA 生成的测试输入可能会大幅降低系统的性能。与原始输入相比，EREBA 生成的测试输入可以使 AdNN 的能耗增加 2,000%。我们的结果还表明，通过 EREBA 生成的测试输入对于检测能量激增输入很有价值。
Recently, various Deep Neural Network (DNN) models have been proposed for environments like embedded systems with stringent energy constraints. The fundamental problem of determining the ro-bustness of a DNN with respect to its energy consumption (energy robustness) is relatively unexplored compared to accuracy-based ro-bustness. This work investigates the energy robustness of Adaptive Neural Networks (AdNNs), a type of energy-saving DNNs proposed for many energy-sensitive domains and have recently gained traction. We propose EREBA, the first black-box testing method for determining the energy robustness of an AdNN. EREBA explores and infers the relationship between inputs and the energy con-sumption of AdNN s to generate energy surging samples. Extensive implementation and evaluation using three state-of-the-art AdNNs demonstrate that test inputs generated by EREBA could degrade the performance of the system substantially. The test inputs gener-ated by EREBA can increase the energy consumption of AdNN s by 2,000% compared to the original inputs. Our results also show that test inputs generated via EREBA are valuable in detecting energy surging inputs.