Amadeus: Scalable, Privacy-Preserving Live Video Analytics

Smart-city applications ranging from traffic management to public-safety alerts rely on live analytics of video from surveillance cameras in public spaces. However, a growing number of government regulations stipulate how data collected from these cameras must be handled in order to protect citizens' privacy. This paper describes Amadeus, which balances privacy and utility by redacting video in near realtime for smart-city applications. Our main insight is that whitelisting objects, or blocking by default, is crucial for scalable, privacy-preserving video analytics. In the context of modern object detectors, we prove that whitelisting reduces the risk of an object-detection error leading to a privacy violation, and helps Amadeus scale to a large and diverse set of applications. In particular, Amadeus utilizes whitelisting to generate composable encrypted object-specific live streams, which simultaneously meet the requirements of multiple applications in a privacy-preserving fashion, while reducing the compute and streaming-bandwidth requirements at the edge. Experiments with our Amadeus prototype show that compared to blacklisting objects, whitelisting yields significantly better privacy (up to ~28x) and bandwidth savings (up to ~5.5x). Additionally, our experiments also indicate that the composable live streams generated by Amadeus are usable by real-world applications with minimum utility loss.

[1]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[2]  Mario Cifrek,et al.  A brief introduction to OpenCV , 2012, 2012 Proceedings of the 35th International Convention MIPRO.

[3]  Tadayoshi Kohno,et al.  SensorSift: balancing sensor data privacy and utility in automated face understanding , 2012, ACSAC '12.

[4]  Lujo Bauer,et al.  Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition , 2016, CCS.

[5]  Ashwin Machanavajjhala,et al.  What You Mark is What Apps See , 2016, MobiSys.

[6]  Vitaly Shmatikov,et al.  A Scanner Darkly: Protecting User Privacy from Perceptual Applications , 2013, 2013 IEEE Symposium on Security and Privacy.

[7]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  Jiri Matas,et al.  Discriminative Correlation Filter with Channel and Spatial Reliability , 2017, CVPR.

[9]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Rui Caseiro,et al.  High-Speed Tracking with Kernelized Correlation Filters , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Ashwin Machanavajjhala,et al.  Olympus: Sensor Privacy through Utility Aware Obfuscation , 2019, Proc. Priv. Enhancing Technol..

[12]  Lorrie Faith Cranor,et al.  A Conundrum of Permissions: Installing Applications on an Android Smartphone , 2012, Financial Cryptography Workshops.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Dan Boneh,et al.  Ensemble Adversarial Training: Attacks and Defenses , 2017, ICLR.

[15]  Weisong Shi,et al.  Edge Computing [Scanning the Issue] , 2019, Proc. IEEE.

[16]  Deirdre K. Mulligan,et al.  Respectful cameras: detecting visual markers in real-time to address privacy concerns , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Seong Joon Oh,et al.  I-Pic: A Platform for Privacy-Compliant Image Capture , 2016, MobiSys.

[18]  G. Broll,et al.  Microsoft Corporation , 1999 .

[19]  Paramvir Bahl,et al.  Focus: Querying Large Video Datasets with Low Latency and Low Cost , 2018, OSDI.

[20]  Minlan Yu,et al.  Wide-area analytics with multiple resources , 2018, EuroSys.

[21]  Hamed Haddadi,et al.  Deep Private-Feature Extraction , 2018, IEEE Transactions on Knowledge and Data Engineering.

[22]  Paramvir Bahl,et al.  Live Video Analytics at Scale with Approximation and Delay-Tolerance , 2017, NSDI.

[23]  Ramesh Govindan,et al.  P3: Toward Privacy-Preserving Photo Sharing , 2013, NSDI.

[24]  Frederic P. Miller,et al.  Advanced Encryption Standard , 2009 .

[25]  Xiaojuan Qi,et al.  ICNet for Real-Time Semantic Segmentation on High-Resolution Images , 2017, ECCV.

[26]  Yixin Chen,et al.  Compressing Neural Networks with the Hashing Trick , 2015, ICML.

[27]  Xiaogang Wang,et al.  Deep Convolutional Network Cascade for Facial Point Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Paramvir Bahl,et al.  VideoEdge: Processing Camera Streams using Hierarchical Clusters , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[29]  Seungyeop Han,et al.  Fast Video Classification via Adaptive Cascading of Deep Models , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Ragunathan Rajkumar,et al.  Quartz: time-as-a-service for coordination in geo-distributed systems , 2019, SEC.

[31]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Brian A. Carter,et al.  Advanced Encryption Standard , 2007 .

[33]  Helen J. Wang,et al.  Enabling Fine-Grained Permissions for Augmented Reality Applications with Recognizers , 2013, USENIX Security Symposium.

[34]  Christof Fetzer,et al.  PrivApprox: Privacy-Preserving Stream Analytics , 2019, Informatik Spektrum.

[35]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[36]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Wenliang Du,et al.  Secure multi-party computation problems and their applications: a review and open problems , 2001, NSPW '01.

[38]  Ion Stoica,et al.  Chameleon: scalable adaptation of video analytics , 2018, SIGCOMM.

[39]  Janusz Konrad,et al.  VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[40]  Iraj Sodagar,et al.  The MPEG-DASH Standard for Multimedia Streaming Over the Internet , 2011, IEEE MultiMedia.

[41]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[42]  Ferdinand van der Heijden,et al.  Efficient adaptive density estimation per image pixel for the task of background subtraction , 2006, Pattern Recognit. Lett..

[43]  Paramvir Bahl,et al.  The Case for VM-Based Cloudlets in Mobile Computing , 2009, IEEE Pervasive Computing.

[44]  Roy Fielding,et al.  Architectural Styles and the Design of Network-based Software Architectures"; Doctoral dissertation , 2000 .

[45]  Krishnaram Kenthapadi,et al.  PriPeARL: A Framework for Privacy-Preserving Analytics and Reporting at LinkedIn , 2018, CIKM.

[46]  Ananthram Swami,et al.  Practical Black-Box Attacks against Machine Learning , 2016, AsiaCCS.

[47]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[48]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[49]  Peter Bailis,et al.  NoScope: Optimizing Deep CNN-Based Queries over Video Streams at Scale , 2017, Proc. VLDB Endow..

[50]  Zhuo Chen,et al.  Edge Analytics in the Internet of Things , 2015, IEEE Pervasive Computing.

[51]  Seong Joon Oh,et al.  Adversarial Image Perturbation for Privacy Protection A Game Theory Perspective , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[52]  Flora Graham,et al.  Daily briefing: San Francisco bans facial-recognition technology , 2019, Nature.

[53]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[54]  Thierry Chateau,et al.  SMC faster R-CNN: Toward a scene-specialized multi-object detector , 2017, Comput. Vis. Image Underst..

[55]  Paramvir Bahl,et al.  Real-Time Video Analytics: The Killer App for Edge Computing , 2017, Computer.

[56]  Mahadev Satyanarayanan,et al.  Edge Computing , 2017, Computer.

[57]  Fabio Tozeto Ramos,et al.  Simple online and realtime tracking , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[58]  Helen J. Wang,et al.  SurroundWeb: Mitigating Privacy Concerns in a 3D Web Browser , 2015, 2015 IEEE Symposium on Security and Privacy.

[59]  Nuno Vasconcelos,et al.  Learning Complexity-Aware Cascades for Deep Pedestrian Detection , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[60]  Ajay Luthra,et al.  Overview of the H.264/AVC video coding standard , 2003, IEEE Trans. Circuits Syst. Video Technol..

[61]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[62]  Mahadev Satyanarayanan,et al.  A Scalable and Privacy-Aware IoT Service for Live Video Analytics , 2017, MMSys.

[63]  M. Vijay Venkatesh,et al.  Privacy Protection for Life-log Video , 2007 .