Authenticating Video Feeds using Electric Network Frequency Estimation at the Edge

Abstract

Large scale Internet of Video Things (IoVT) supports situation awareness for smart cities; however, the rapid development in artificial intelligence (AI) technologies enables fake video/audio streams and doctored images to fool smart city security operators. Authenticating visual/audio feeds becomes essential for safety and security, from which an Electric Network Frequency (ENF) signal collected from the power grid is a prominent authentication mechanism. This paper proposes an ENF-based Video Authentication method using steady Superpixels (EVAS). Video superpixels group the pixels with uniform intensities and textures to eliminate the impacts from the fluctuations in the ENF estimation. An extensive experimental study validated the effectiveness of the EVAS system. Aiming at the environments with interconnected surveillance camera systems at the edge powered by an electricity grid, the proposed EVAS system achieved the design goal of detecting dissimilarities in the image sequences.

Keywords

• video data authentication
• electrical network frequency (enf) estimation
• internet of video things (iovt)
• edge computing
• visual layer backdoor attacks