Privacy and Security in Video Surveillance
01 Jan 2013-pp 37-66
TL;DR: This chapter motivates the need for the integration of security and privacy features, discusses fundamental requirements and provides a comprehensive review of the state of the art of video surveillance systems.
Abstract: Video surveillance systems are usually installed to increase the safety and security of people or property in the monitored areas. Typical threat scenarios are robbery, vandalism, shoplifting or terrorism. Other application scenarios are more intimate and private such as home monitoring or assisted living. For a long time, it was accepted that the potential benefits of video surveillance go hand in hand with a loss of personal privacy. However, with the on-board processing capabilities of modern embedded systems it becomes possible to compensate this privacy loss by making security and privacy protection inherent features of video surveillance cameras. In the first part of this chapter, we motivate the need for the integration of security and privacy features, we discuss fundamental requirements and provide a comprehensive review of the state of the art. The second part presents the TrustCAM prototype system where a dedicated hardware security module is integrated into a camera system to achieve a high level of security. The chapter is concluded by a summary of open research issues and an outlook to future trends.
Citations
More filters
TL;DR: In this article, the authors provide a comprehensive introduction to privacy-related research in the area of biometrics and review existing work on Biometric Privacy-Enhancing Techniques (B-PETs) applied to face recognition technology.
Abstract: Biometric recognition technology has made significant advances over the last decade and is now used across a number of services and applications. However, this widespread deployment has also resulted in privacy concerns and evolving societal expectations about the appropriate use of the technology. For example, the ability to automatically extract age, gender, race, and health cues from biometric data has heightened concerns about privacy leakage. Face recognition technology, in particular, has been in the spotlight, and is now seen by many as posing a considerable risk to personal privacy. In response to these and similar concerns, researchers have intensified efforts towards developing techniques and computational models capable of ensuring privacy to individuals, while still facilitating the utility of face recognition technology in several application scenarios. These efforts have resulted in a multitude of privacy–enhancing techniques that aim at addressing privacy risks originating from biometric systems and providing technological solutions for legislative requirements set forth in privacy laws and regulations, such as GDPR. The goal of this overview paper is to provide a comprehensive introduction into privacy–related research in the area of biometrics and review existing work on Biometric Privacy–Enhancing Techniques (B–PETs) applied to face biometrics. To make this work useful for as wide of an audience as possible, several key topics are covered as well, including evaluation strategies used with B–PETs, existing datasets, relevant standards, and regulations and critical open issues that will have to be addressed in the future.
37 citations
01 Oct 2019
TL;DR: A deep learning-based compressive sensing approach to reconstruct and protect sensitive regions from secured FlatCam measurements via facial segmentation and separate them from the captured measurements is proposed.
Abstract: Detection followed by projection in conventional privacy cameras is vulnerable to software attacks that threaten to expose image sensor data. By multiplexing the incoming light with a coded mask, a FlatCam camera removes the spatial correlation and captures visually protected images. However, FlatCam imaging suffers from poor reconstruction quality and pays no attention to the privacy of visual information. In this paper, we propose a deep learning-based compressive sensing approach to reconstruct and protect sensitive regions from secured FlatCam measurements. We predict sensitive regions via facial segmentation and separate them from the captured measurements. Our deep compressive sensing network was trained with simulated data, and was tested on both simulated and real FlatCam data.
17 citations
TL;DR: In this paper, a classification of research on video data security based on the collection and analysis of related works is presented, and an analysis of the research on VDS technologies combined with intelligent technologies based on SLR methodology.
Abstract: A range of video contents and technology have provided convenience to humans, with real-time video applications—such as surveillance applications—able to contribute to increasing public safety by reducing physical crimes. The development of video technology has made it possible to achieve an improved quality of life. However, this technology can also be exploited and lead to security issues such as physical and digital crimes. Unfortunately, security breaches are increasing in complexity and frequency, making current countermeasures insufficient to prevent them. Given recent trends, we recognize the need for security technology to respond to advanced video crimes. Intelligent security is one of the methods that can be used to respond to these issues. Although research on video data security has been actively conducted, not enough studies have been published on video data security that also addresses intelligent security. Specifically, a classification system for research on video data security has not been provided, and no systematic analysis has been conducted for advanced research. Thus, the purpose of this is to fill in these gaps in existing research. This study offers a classification of research on video data security based on the collection and analysis of related works. Moreover, this study presents an analysis of research on video data security technologies combined with intelligent technologies based on SLR methodology.
11 citations
TL;DR: A trusted camera based on PUFs and standard cryptographic algorithms is proposed and a protocol is proposed to protect the communication with the trusted camera, which satisfies authentication, confidentiality, integrity and freshness in the data communication.
Abstract: This work was supported in part by TEC2014-57971-R and TEC2017-83557-R projects from Ministerio de Ciencia, Innovacion y Universidades of the Spanish Government (with support from the PO FEDER-FSE) and 201750E010 (HW-SEEDS) project from CSIC. The work of Rosario Arjona was supported by a Post-Doc Fellowship from the Spanish National Cybersecurity Institute (INCIBE). The work of Miguel A. Prada-Delgado was supported by V Plan Propio de Investigacion through the University of Seville.
6 citations
01 Jan 2020
TL;DR: The authors review solutions related to migrating machine learning based inference towards edge and smart client devices, as well as methods for DDoS (Distributed Denial of Service) intelligent detection, where DDoS attack is recognized as one of the primary concerns in cybersecurity.
Abstract: Artificial intelligence is making significant changes in industrial internet of things (IIoT). Particularly, machine and deep learning architectures are now used for cybersecurity in smart factories, smart homes, and smart cities. Using advanced mathematical models and algorithms more intelligent protection strategies should be developed. Hacking of IP surveillance camera systems and Closed-Circuit TV (CCTV) vulnerabilities represent typical example where cyber attacks can make severe damage to physical and other Industrial Control Systems (ICS). This chapter analyzes the possibilities to provide better protection of video surveillance systems and communication networks. The authors review solutions related to migrating machine learning based inference towards edge and smart client devices, as well as methods for DDoS (Distributed Denial of Service) intelligent detection, where DDoS attack is recognized as one of the primary concerns in cybersecurity.
5 citations
References
More filters
TL;DR: The digital signature standard (DSS) as mentioned in this paper was proposed to authenticate electronic mail messages by using modern cryptographic techniques to prevent the explosion of very capable personal computers from driving up the incidence of doctored photographs being passed off as truth.
Abstract: The trustworthy digital camera is an application of existing technology toward the solution of an evermore-troubling social problem, the eroding credibility of the photographic image. Although it will always be possible to lie with a photograph (using such time-honored techniques as false perspective and misleading captions), this proposed device will prevent the explosion of very capable personal computers from driving up the incidence of doctored photographs being passed off as truth. A solution to this problem comes from the proposed digital signature standard (DSS), which incorporates modern cryptographic techniques to authenticate electronic mail messages. >
502 citations
16 Sep 1996
TL;DR: The results show the ability of the texture analysis techniques used to discriminate clot lesions, and highlights the advantage of using the raw data over the scan-converted data in assessing thrombus composition in vitro.
Abstract: Thrombosis of coronary arteries is a condition responsible for many acute coronary syndromes. The ability to categorise thrombus belonging to distinct pathological groups, would contribute to the understanding of the pathophysiologic structure of individual lesions, as well as making a significant contribution to treatment choice. Here, the authors investigate the use of statistical texture analysis techniques to assess the ability of 30 MHz intravascular ultrasound (IVUS) data, in raw and scan-converted form, to characterise intracoronary thrombus. Three clot types were assessed in the study, these were, red (R), white (W) and plasma (P). Histopathological analysis, the de facto standard in identifying tissue composition, was used to form a Gold Standard based upon clot composition, from which the results were verified. The results show the ability of the texture analysis techniques used to discriminate clot lesions, and highlights the advantage of using the raw data over the scan-converted data in assessing thrombus composition in vitro.
431 citations
TL;DR: To further improve the procedures, several extensions to the Feige-Fiat-Shamir (1987) digital signature scheme are proposed to substantially speed up both the signing and verification operations, as well as to allow "adjustable and incremental" verification.
Abstract: We present chaining techniques for signing/verifying multiple packets using a single signing/verification operation. We then present flow signing and verification procedures based upon a tree-chaining technique. Since a single signing/verification operation is amortized over many packets, these procedures improve signing and verification rates by one to two orders of magnitude, compared to the approach of signing/verifying packets individually. Our procedures do not depend upon reliable delivery of packets. They also provide delay-bounded signing, and are thus suitable for delay-sensitive flows and multicast applications. To further improve our procedures, we propose several extensions to the Feige-Fiat-Shamir (1987) digital signature scheme to substantially speed up both the signing and verification operations, as well as to allow "adjustable and incremental" verification. The extended scheme, called eFFS, is compared to four other digital signature schemes (RSA, DSA, ElGamal (1985), and Rabin). We compare their signing and verification times, as well as key and signature sizes. We observe that: (1) eFFS is the fastest in signing (by a large margin over any of the other four schemes) and as fast as RSA in verification (tie for a close second behind Rabin (1979)); (2) eFFS allows a tradeoff between memory and signing/verification time; and (3) eFFS allows adjustable and incremental verification by receivers.
332 citations
06 Feb 2010
TL;DR: The spatial content production model (SCPM) is introduced as a possible factor in the localness of UGC, and other theoretical and applied implications are discussed.
Abstract: The "localness" of participation in repositories of user-generated content (UGC) with geospatial components has been cited as one of UGC's greatest benefits. However, the degree of localness in major UGC repositories such as Flickr and Wikipedia has never been examined. We show that over 50 percent of Flickr users contribute local information on average, and over 45 percent of Flickr photos are local to the photographer. Across four language editions of Wikipedia, however, we find that participation is less local. We introduce the spatial content production model (SCPM) as a possible factor in the localness of UGC, and discuss other theoretical and applied implications.
320 citations