Advanced computer vision technology can provide near real-time home monitoring to support "aging in place" by detecting falls and symptoms related to seizures and stroke. Affordable webcams, together with cloud computing services (to run machine learning algorithms), can potentially bring significant social benefits. However, it has not been deployed in practice because of privacy concerns. In this paper, we propose a strategy that uses homomorphic encryption to resolve this dilemma, which guarantees information confidentiality while retaining action detection. Our protocol for secure inference can distinguish falls from activities of daily living with 86.21% sensitivity and 99.14% specificity, with an average inference latency of 1.2 seconds and 2.4 seconds on real-world test datasets using small and large neural nets, respectively. We show that our method enables a 613x speedup over the latency-optimized LoLa and achieves an average of 3.1x throughput increase in secure inference compared to the throughput-optimized nGraph-HE2.
翻译:先进的计算机视觉技术可以提供近实时的家庭监测,通过检测与缉获和中风有关的瀑布和症状来支持“就地工作”。可负担得起的网络摄像头,加上云计算服务(运行机器学习算法),可以带来巨大的社会效益。然而,由于隐私问题,尚未实际应用这种技术。在本文中,我们提议一项战略,利用同质加密来解决这一难题,保证信息保密,同时保留行动探测。我们的安全推断程序可以区别于日常生活活动,其敏感度为86.21%,特异性为99.14%,使用小型和大型神经网,在现实世界测试数据集中的平均推导力分别为1.2秒和2.4秒。我们表明,我们的方法可以加速613x的Latenentency-opimized LoLoLa速度,并实现平均3.1x通过安全传输增加的3.1倍。