arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09164cs.CR
收藏

基于加密神经网络推理的安全人体动作识别

Secure Human Action Recognition by Encrypted Neural Network Inference

Miran Kim, Xiaoqian Jiang, Kristin Lauter, Elkhan Ismayilzada, Shayan Shams

摘要:

先进的计算机视觉技术可以提供近乎实时的家庭监测,通过检测跌倒以及与癫痫发作和中风相关的症状,支持“就地养老”。经济实惠的网络摄像头,加上云计算服务(运行机器学习算法),可能会带来巨大的社会效益。然而,由于隐私问题,它尚未在实践中部署。在本文中,我们提出了一种策略,使用同态加密来解决这个困境,它保证信息的机密性,同时保留动作检测。我们的安全推理协议可以区分跌倒与日常生活活动,灵敏度为86.21%,特异性为99.14%,使用小型和大型神经网络的真实测试数据集的平均推理延迟分别为1.2秒和2.4秒。我们表明,与延迟优化的LoLa相比,我们的方法实现了613倍的加速,并且与吞吐量优化的nGraph-HE 2相比,安全推理的吞吐量平均增加了3.1倍。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑