Security-Preserving Live 3D Video Surveillance
Pages 266 - 277
Abstract
3D video surveillance has become the new trend in security monitoring with the popularity of 3D depth cameras in the consumer market. While enabling more fruitful surveillance features, the finer-grained 3D videos being captured would raise new security concerns that have not been addressed by existing research. This paper explores the security implications of live 3D surveillance videos in triggering biometrics-related attacks, such as face ID spoofing. We demonstrate that the state-of-the-art face authentication systems can be effectively compromised by the 3D face models presented in the surveillance video. Then, to defend against such face spoofing attacks, we propose to proactively and benignly inject adversarial perturbations to the surveillance video in real time, prior to the exposure to potential adversaries. Such dynamically generated perturbations can prevent the face models from being exploited to bypass deep learning-based face authentications while maintaining the required quality and functionality of the 3D video surveillance. We evaluate the proposed perturbation generation approach on both an RGB-D dataset and a 3D video dataset, which justifies its effective security protection, low quality degradation, and real-time performance.
References
[1]
2015. KinectDocs. https://github.com/Kinect/Docs.
[2]
2017. Apple Event Keynote 2017: iPhoneX Face ID and Animoji. https://www.youtube.com/watch?v=eRvBU_tKGjE.
[3]
2017. Windows 10's face authentication defeated with a picture. https://www.theverge.com/2017/12/21/16804992/microsoft-windows-10-windows-hello-bypass-security.
[4]
2017. Windows Hello face authentication. https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/windows-hello-face-authentication.
[5]
2019. 3D machine vision guides robotic system for logistics e-fulfillment. https://www.vision-systems.com/cameras-accessories/article/16736111/3d-machine-vision-guides-robotic-system-for-logistics-efulfillment.
[6]
2019. CosineSimilarity - PyTorch Docs. https://pytorch.org/docs/stable/generated/torch.nn.CosineSimilarity.html.
[7]
2019. How 3D sensors are transforming the transportation and logistics industry. https://www.zebra.com/us/en/blog/posts/2019/this-one-technology-is-delivering-a-solution-to-the-parcel-problem.html.
[8]
2020. Balancing privacy concerns with video monitoring capabilities. https://www.sdmmag.com/articles/98278-balancing-privacy-concerns-with-video-monitoring-capabilities.
[9]
2020. DepthKit. https://depthkit.tv.
[10]
2020. Online face recognition software demo - The BioID playground. https://www.bioid.com/playground/.
[11]
2021. 3D camera market size, share and trends analysis report. https://www.grandviewresearch.com/industry-analysis/3d-camera-market.
[12]
2021. Cash withdrawal in an ATM with face biometrics - Use case. https://www.electronicid.eu/en/blog/post/cash-withdrawal-atm-face-biometrics/en.
[13]
2021. Time-of-flight camera - An introduction. https://www.mouser.com/applications/time-of-flight-robotics/.
[14]
2021. Why 3D is the key to unlocking vital video surveillance data. https://oyla.ai/why-3d-is-the-key-to-unlocking-vital-video-surveillance-data/.
[15]
2021. ZED 2 camera. https://www.stereolabs.com/zed-2/.
[16]
2022. 3D surveillance with Leica BLK247 and CORTROL VMS: Smart 3D surveillance system. https://ganzsecurity.com/subpage/1308/3d-surveillance-with-leica-geosystems-blk247-and-cortrol.
[17]
2022. Mastercard launches tech that lets you pay with your face or hand in stores. https://www.cnbc.com/2022/05/17/mastercard-launches-tech-that-lets-you-pay-with-your-face-or-hand.html.
[18]
2022. TSA PreCheck: Touchless identity solution. https://www.tsa.gov/biometrics-technology/evaluating-facial-identification-technology.
[19]
2023. Spectrum series 3D people counter. https://www.trafsys.com/spectrum-3d-people-counter/.
[20]
Shivang Aggarwal, Sibendu Paul, Pranab Dash, Nuka Saranya Illa, Y Charlie Hu, Dimitrios Koutsonikolas, and Zhisheng Yan. 2020. How to evaluate mobile 360° video streaming systems?. In International Workshop on Mobile Computing Systems and Applications (HotMobile). 68--73.
[21]
Abdullah Al Arafat, Zhishan Guo, and Amro Awad. 2021. VR-Spy: A Side-Channel Attack on Virtual Key-Logging in VR Headsets. In 2021 IEEE Virtual Reality and 3D User Interfaces (VR). 564--572.
[22]
Bijie Bai, Yi Luo, Tianyi Gan, Jingtian Hu, Yuhang Li, Yifan Zhao, Deniz Mengu, Mona Jarrahi, and Aydogan Ozcan. 2022. To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects. arXiv preprint arXiv:2205.13122 (2022).
[23]
Efe Bozkir, Onur Günlü, Wolfgang Fuhl, Rafael F Schaefer, and Enkelejda Kasneci. 2021. Differential privacy for eye tracking with temporal correlations. Plos one 16, 8 (2021), e0255979.
[24]
Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In IEEE Symposium on Security and Privacy (S&P). 39--57.
[25]
Huangxun Chen, Wei Wang, Jin Zhang, and Qian Zhang. 2019. EchoFace: Acoustic Sensor-Based Media Attack Detection for Face Authentication. IEEE Internet of Things Journal 7, 3 (2019), 2152--2159.
[26]
Jiankang Deng, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. 2019. Arcface: Additive angular margin loss for deep face recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4690--4699.
[27]
Nguyen Minh Duc and Bui Quang Minh. 2009. Your face is not your password face authentication bypassing lenovo-asus-toshiba. Black Hat Briefings 4 (2009), 158.
[28]
Serhan Gül, Dimitri Podborski, Thomas Buchholz, Thomas Schierl, and Cornelius Hellge. 2020. Low-Latency Cloud-Based Volumetric Video Streaming Using Head Motion Prediction. 27--33.
[29]
Chuan Guo, Mayank Rana, Moustapha Cisse, and Laurens Van Der Maaten. 2017. Countering adversarial images using input transformations. arXiv preprint arXiv:1711.00117 (2017).
[30]
Qingying Hao, Licheng Luo, Steve TK Jan, and Gang Wang. 2021. It's not what it looks like: Manipulating perceptual hashing based applications. In ACM Conference on Computer and Communications Security (CCS). 69--85.
[31]
RI Hg, Petr Jasek, Clement Rofidal, Kamal Nasrollahi, Thomas B Moeslund, and Gabrielle Tranchet. 2012. An RGB-D database using Microsoft's Kinect for Windows for Face Detection. In International Conference on Signal Image Technology and Internet Based Systems. 42--46.
[32]
Suman Jana, David Molnar, Alexander Moshchuk, Alan Dunn, Benjamin Livshits, Helen J Wang, and Eyal Ofek. 2013. Enabling fine-grained permissions for augmented reality applications with recognizers. In USENIX Security Symposium (Security). 415--430.
[33]
Suman Jana, Arvind Narayanan, and Vitaly Shmatikov. 2013. A scanner darkly: Protecting user privacy from perceptual applications. In IEEE Symposium on Security and Privacy (S&P). 349--363.
[34]
Pavel Korshunov, Claudia Araimo, Francesca De Simone, Carmelo Velardo, J-L Dugelay, and Touradj Ebrahimi. 2012. Subjective study of privacy filters in video surveillance. In International Workshop on Multimedia Signal Processing (MMSP). 378--382.
[35]
Alexey Kurakin, Ian Goodfellow, and Samy Bengio. 2016. Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016).
[36]
Jean Le Feuvre, Cyril Concolato, Nassima Bouzakaria, and Viet-Thanh-Trung Nguyen. 2015. MPEG-DASH for low latency and hybrid streaming services. In ACM international conference on Multimedia (MM). 751--752.
[37]
Jean Le Feuvre, Cyril Concolato, and Jean-Claude Moissinac. 2007. GPAC: open source multimedia framework. In ACM international conference on Multimedia (MM). 1009--1012.
[38]
Kiron Lebeck, Kimberly Ruth, Tadayoshi Kohno, and Franziska Roesner. 2017. Securing augmented reality output. In IEEE Symposium on Security and Privacy (S&P). 320--337.
[39]
Jingjie Li, Amrita Roy Chowdhury, Kassem Fawaz, and Younghyun Kim. 2021. Kalεido: Real-time privacy control for eye-tracking systems. In USENIX Security Symposium (Security). 1793--1810.
[40]
Yan Li, Yingjiu Li, Qiang Yan, Hancong Kong, and Robert H. Deng. 2015. Seeing your face is not enough: An inertial sensor-based liveness detection for face authentication. In ACM Conference on Computer and Communications Security (CCS). 1558--1569.
[41]
Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, and Le Song. 2017. Sphereface: Deep hypersphere embedding for face recognition. In IEEE conference on computer vision and pattern recognition (CVRP). 212--220.
[42]
Shiqing Luo, Anh Nguyen, Chen Song, Feng Lin, Wenyao Xu, and Zhisheng Yan. 2020. OcuLock: Exploring human visual system for authentication in virtual reality head-mounted display. In The Network and Distributed System Security Symposium (NDSS).
[43]
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu.2017. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017).
[44]
Florian Mathis, John H Williamson, Kami Vaniea, and Mohamed Khamis. 2021. Fast and secure authentication in virtual reality using coordinated 3D manipulation and pointing. ACM Transactions on Computer-Human Interaction (ToCHI) 28, 1 (2021), 1--44.
[45]
Yue Ming and Xiaopeng Hong. 2016. A unified 3D face authentication framework based on robust local mesh SIFT feature. Neurocomputing 184 (2016), 117--130.
[46]
Abdelmalik Ouamane, Mebarka Belahcene, Abdelhamid Benakcha, Salah Bourennane, and Abdelmalik Taleb-Ahmed. 2016. Robust multimodal 2D and 3D face authentication using local feature fusion. Signal, Image and Video Processing 10, 1 (2016), 129--137.
[47]
Norman Di Palo. 2018. How I implemented iPhone X's FaceID using deep learning in Python. https://towardsdatascience.com/how-i-implemented-iphone-xs-faceid-using-deep-learning-in-python-d5dbaa128e1d
[48]
Fei Peng, Xiao-wen Zhu, and Min Long. 2013. An ROI privacy protection scheme for H. 264 video based on FMO and chaos. IEEE Transactions on Information Forensics and Security 8, 10 (2013), 1688--1699.
[49]
Huy Phan, Yi Xie, Siyu Liao, Jie Chen, and Bo Yuan. 2020. CAG: A real-time low-cost enhanced-robustness high-transferability content-aware adversarial attack generator. In AAAI Conference on Artificial Intelligence (AAAI), Vol. 34. 5412--5419.
[50]
Francesco Pittaluga, Aleksandar Zivkovic, and Sanjeev J Koppal. 2016. Sensor-level privacy for thermal cameras. In International Conference on Computational Photography (ICCP). 1--12.
[51]
Omid Poursaeed, Isay Katsman, Bicheng Gao, and Serge Belongie. 2018. Generative adversarial perturbations. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4422--4431.
[52]
Feng Qian, Bo Han, Jarrell Pair, and Vijay Gopalakrishnan. 2019. Toward practical volumetric video streaming on commodity smartphones. In International Workshop on Mobile Computing Systems and Applications (HotMobile). 135--140.
[53]
Slobodan Ribaric and Nikola Pavesic. 2015. An overview of face de-identification in still images and videos. In IEEE International conference and workshops on automatic face and gesture recognition (FG), Vol. 4. 1--6.
[54]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. 234--241.
[55]
Kimberly Ruth, Tadayoshi Kohno, and Franziska Roesner. 2019. Secure multi-user content sharing for augmented reality applications. In USENIX Security Symposium (Security). 141--158.
[56]
Arash Shafiei, Cyril Concolato, and Jean Le Feuvre. 2013. DashCast, a live DASH streaming server. In International Workshop on Multimedia Signal Processing (MMSP).
[57]
Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First order motion model for image animation. Advances in Neural Information Processing Systems 32 (2019).
[58]
Iraj Sodagar. 2011. The MPEG-DASH standard for multimedia streaming over the Internet. IEEE MultiMedia 18, 4 (2011), 62--67.
[59]
Julian Steil, Marion Koelle, Wilko Heuten, Susanne Boll, and Andreas Bulling. 2019. Privaceye: privacy-preserving head-mounted eye tracking using egocentric scene image and eye movement features. In ACM Symposium on Eye Tracking Research & Applications. 1--10.
[60]
Pu Sun, Yuezun Li, Honggang Qi, and Siwei Lyu. 2020. Landmark breaker: Obstructing Deepfake by disturbing landmark extraction. In 2020 IEEE International Workshop on Information Forensics and Security (WIFS). 1--6.
[61]
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv.1312.6199 (2013).
[62]
Zhongze Tang, Xianglong Feng, Yi Xie, Huy Phan, Tian Guo, Bo Yuan, and Sheng Wei. 2020. VVSec code on GitHub. https://github.com/hwsel/vvsec.
[63]
Zhongze Tang, Xianglong Feng, Yi Xie, Huy Phan, Tian Guo, Bo Yuan, and Sheng Wei. 2020. VVSec: Securing volumetric video streaming via benign use of adversarial perturbation. In ACM International Conference on Multimedia (MM). 3614--3623.
[64]
Robert Templeman, Mohammed Korayem, David J Crandall, and Apu Kapadia. 2014. PlaceAvoider: Steering first-person cameras away from sensitive spaces. In The Network and Distributed System Security Symposium (NDSS). 23--26.
[65]
Suramya Tomar. 2006. Converting video formats with FFmpeg. Linux Journal 2006, 146 (2006), 10.
[66]
Jeroen van der Hooft, Tim Wauters, Filip De Turck, Christian Timmerer, and Hermann Hellwagner. 2019. Towards 6DoF HTTP adaptive streaming through point cloud compression. In ACM Multimedia Conference. 2405--2413.
[67]
Lingxiao Wang, Yali Li, and Shengjin Wang. 2018. Feature learning for one-shot face recognition. In IEEE International Conference on Image Processing (ICIP). 2386--2390.
[68]
Mika Westerlund. 2019. The emergence of Deepfake technology: A review. Technology Innovation Management Review 9, 11 (2019).
[69]
Yi Xu, True Price, Jan-Michael Frahm, and Fabian Monrose. 2016. Virtual U: Defeating face liveness detection by building virtual models from your public photos. In USENIX Security Symposium (Security). 497--512.
[70]
Zirui Xu, Fuxun Yu, Chenchen Liu, and Xiang Chen. 2019. HAMPER: high-performance adaptive mobile security enhancement against malicious speech and image recognition. In Asia and South Pacific Design Automation Conference (ASPDAC). 512--517.
[71]
Chao-Han Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma, and Chin-Hui Lee. 2020. Characterizing speech adversarial examples using self-attention u-net enhancement. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 3107--3111.
[72]
Xiaowen Ying, Xin Li, and Mooi Choo Chuah. 2018. LiveFace: A multi-task CNN for fast face-authentication. In International Conference on Machine Learning and Applications (ICMLA). 955--960.
[73]
Fuxun Yu, Zirui Xu, Chenchen Liu, and Xiang Chen. 2019. Masker: Adaptive mobile security enhancement against automatic speech recognition in eavesdropping. In Annual Design Automation Conference (DAC). 1--6.
[74]
Hyunwoo Yu, Jaemin Lim, Kiyeon Kim, and Suk-Bok Lee. 2018. Pinto: Enabling video privacy for commodity IoT cameras. In ACM SIGSAC Conference on Computer and Communications Security (CCS). 1089--1101.
[75]
Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. LPIPS code on GitHub. https://github.com/richzhang/PerceptualSimilarity.
[76]
Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The unreasonable effectiveness of deep features as a perceptual Metric. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 586--595.
[77]
Wei Zhang, S.S. Cheung, and Minghua Chen. 2005. Hiding privacy information in video surveillance system. In IEEE International Conference on Image Processing (ICIP), Vol. 3. II--868.
[78]
Bing Zhou, Zongxing Xie, and Fan Ye. 2019. Multi-modal face authentication using deep visual and acoustic features. In IEEE International Conference on Communications (ICC). 1--6.
[79]
IOhannes M Zmölnig. 2005. v4l2loopback - a kernel module to create V4L2 loopback devices. https://github.com/umlaeute/v4l2loopback.
Index Terms
- Security-Preserving Live 3D Video Surveillance
Recommendations
Security of CCTV and Video Surveillance Systems: Threats, Vulnerabilities, Attacks, and Mitigations
TrustED '16: Proceedings of the 6th International Workshop on Trustworthy Embedded DevicesVideo surveillance, closed-circuit TV and IP-camera systems became virtually omnipresent and indispensable for many organizations, businesses, and users. Their main purpose is to provide physical security, increase safety, and prevent crime. They also ...
Face recognition performance comparison between fake faces and live faces
Face recognition is a widely used biometric technology because it is both user friendly and more convenient to use than other biometric approaches. However, naïve face recognition systems that do not support any type of liveness detection can be easily ...
A LBP Texture Analysis Based Liveness Detection for Face Authentication
Machine Learning for Cyber SecurityAbstractFace authentication systems are becoming more and more prevalent, but it has an intrinsic vulnerability against the media-based face forgery (MFF) where adversaries display photos or videos containing victims’ faces to deceive face authentication ...
Comments
Information & Contributors
Information
Published In
June 2023
495 pages
ISBN:9798400701481
DOI:10.1145/3587819
- Co-chairs:
- Shervin Shirmohammadi,
- Mohamed Hefeeda,
- Program Co-chairs:
- Roger Zimmermann,
- Carsten Griwodz,
- Mea Wang
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 June 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
Conference
MMSys '23
Sponsor:
Acceptance Rates
Overall Acceptance Rate 176 of 530 submissions, 33%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 280Total Downloads
- Downloads (Last 12 months)165
- Downloads (Last 6 weeks)21
Reflects downloads up to 26 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in