HDXplore: Automated Blackbox Testing of Brain-Inspired Hyperdimensional Computing
HDXplore: Automated Blackbox Testing of Brain-Inspired Hyperdimensional Computing
复制标题
HDXplore：类脑超维计算的自动化黑盒测试
DOI：
10.1109/isvlsi51109.2021.00027
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Xun Jiao
中科院分区：
文献类型：
--
作者：
Rahul Thapa;Dongning Ma;Xun Jiao
受人脑工作方式的启发，新兴的超维计算（HDC）正受到越来越多的关注。HDC是一种新兴的基于大脑工作机制的计算方案，它利用深层的、抽象的神经活动模式而不是实际的数字进行计算。与DNN等传统ML算法相比，HDC更以内存为中心，具有模型大小相对较小、计算成本较低和一次性学习等优点，使其成为低成本计算平台中有前途的候选者。然而，HDC模型的鲁棒性还没有得到系统的研究。在本文中，我们通过开发HDXplore，一个基于黑盒差分测试的框架，系统地揭示了HDC模型的意外或不正确的行为。我们利用多个HDC模型，这些模型具有与交叉引用Oracle类似的功能，以避免手动检查或标记原始输入。我们还提出了不同的扰动机制在HDXplore。HDXplore自动发现HDC模型的数千个不正确的极端情况行为。我们提出了两种再训练机制，并使用HDXplore生成的角点案例来重新训练HDC模型，我们可以将模型精度提高9%。
Inspired by the way human brain works, the emerging hyperdimensional computing (HDC) is getting more and more attention. HDC is an emerging computing scheme based on the working mechanism of brain that computes with deep and abstract patterns of neural activity instead of actual numbers. Compared with traditional ML algorithms such as DNN, HDC is more memory-centric, granting it advantages such as relatively smaller model size, less computation cost, and one-shot learning, making it a promising candidate in low-cost computing platforms. However, the robustness of HDC models have not been systematically studied. In this paper, we systematically expose the unexpected or incorrect behaviors of HDC models by developing HDXplore, a blackbox differential testing-based framework. We leverage multiple HDC models with similar functionality as crossreferencing oracles to avoid manual checking or labeling the original input. We also propose different perturbation mechanisms in HDXplore. HDXplore automatically finds thousands of incorrect corner case behaviors of the HDC model. We propose two retraining mechanisms and using the corner cases generated by HDXplore to retrain the HDC model, we can improve the model accuracy by up to 9%.
简短的行业论文：HDAD：基于超维计算的汽车传感器攻击异常检测
DOI：
10.1109/rtas52030.2021.00052
发表时间：
2021
期刊：
2021 IEEE 27th Real-Time and Embedded Technology and Applications Symposium (RTAS
影响因子：
--
作者：
Wang, Ruixuan;Kong, Fanxin;Sudler, Hasshi;Jiao, Xun
通讯作者：
Jiao, Xun