Chu K.-Y.Kuo Y.-H.WINSTON HSU2019-07-102019-07-1020139781450324045https://scholars.lib.ntu.edu.tw/handle/123456789/412982https://www.scopus.com/inward/record.uri?eid=2-s2.0-84887435935&doi=10.1145%2f2502081.2502157&partnerID=40&md5=88c127662426835e74d9741bbd142c0dWith the advance of cloud computing, growing applications have been migrating to the cloud for its robustness and scalability. However, sending raw data to the cloud-based ser- vice providers will generally risk our privacy; especially for cloud-based surveillance system, where privacy is one of the major concerns as continuously recording daily life. Thus, privacy-preserving intelligent analytics are in dire needs. In this preliminary research, we investigate real-time privacy- preserving moving object detection in the encrypted cloud- based surveillance videos. Moving object detection is one of the core techniques and can further enable other applications (e.g., object tracking, action recognition, etc.). One possible approach is using homomorphic encryption which provides corresponding operations between unencrypted and encrypted data. However, homomorphic encryption is impractical in real case because of formidable computations and bulky storage consumption. In this paper, we pro- pose an efficient and secure encryption framework, which entails real-time analytics (e.g., moving object detection) in encrypted video streams. Experiments confirm that the pro- posed method can achieve similar accuracy as detection on original raw frames. Copyright ? 2013 ACM.Privacy-preserving surveillance; Real-time detectionAction recognition; Ho-momorphic encryptions; Moving-object detection; Privacy preserving; Privacy preserving surveillance; Real-time analytics; Real-time detection; Surveillance systems; Digital storage; Object recognition; Security systems; Video streaming; Cryptographyconference paper10.1145/2502081.25021572-s2.0-84887435935