The First International Workshop on
The Bright and Dark Sides of Computer Vision:
Challenges and Opportunities for Privacy and Security
Hawaii Convention Center, Honolulu, Hawaii — July 21, 2017
In conjunction with the 2017 IEEE Conference on Computer Vision and Pattern Recognition
— May 26: We are now accepting travel grant applications for students with accepted papers. See the application for more details!
— April 29: Thanks to generous sponsors, we anticipate offering partial travel support to a limited number of students attending the workshop! Priority will go to students presenting papers and abstracts at the workshop. More details and an application form will be posted soon.
— April 21: Full paper submissions are closed, but extended abstract deadline extended until May 15!
Computer vision is finally working in the real world, but what are the consequences on privacy and security? For example, recent work shows that vision algorithms can spy on smartphone keypresses from meters away, steal information from inside homes via hacked cameras, exploit social media to de-anonymize blurred faces, and reconstruct images from features like SIFT. Vision could also enhance privacy and security, for example through assistive devices for people with disabilities, phishing detection techniques that incorporate visual features, and image forensic tools. Some technologies present both challenges and opportunities: biometrics techniques could enhance security but may be spoofed, while surveillance systems enhance safety but create potential for abuse.
We need to understand the potential threats and opportunities of vision to avoid creating detrimental societal effects and/or facing public backlash. This workshop will explore the intersection between computer vision and security and privacy to address these issues.
We welcome original research papers and extended abstracts on topics including, but not limited to:
Research papers should contain original, unpublished research, and be 4-8 pages (excluding references). Research papers will be published in the CVPR Workshop Proceedings and archived on IEEE eXplore and the Computer Vision Foundation websites.
Extended abstracts about preliminary, ongoing or published work should be up to 2 pages (including references). Extended abstracts will be published and archived on this website.
All submissions should be anonymized and will undergo double-blind peer review. Papers and abstracts must be formatted according to the CVPR guidelines and submitted via the Conference Management Toolkit website. Accepted submissions will be invited for oral or poster presentation at the workshop.
Full paper submission deadline:
April 7, April 17 April 19, 11:59PM Pacific Daylight Time (PDT), via CMT.
Abstract submission deadline:
April 7, May 15, 11:59PM Pacific Daylight Time (PDT), via CMT.
Author notification date:
May 1 May 3 (full papers), May 20 (abstracts)
Camera ready deadline: May 17, 11:59PM PDT
|08:00||Coffee and light breakfast|
|08:30||Invited Talk: Towards a Visual Privacy Advisor: Understanding and Controlling Privacy in Visual Data, Mario Fritz (Max Planck)|
|— Deceiving Google’s Cloud Video Intelligence API Built for Summarizing Videos |
Hossein Hosseini, Baicen Xiao, Radha Poovendran (University of Washington)
|— Simple Black-Box Adversarial Attacks on Deep Neural Networks |
Nina Narodytska (VMware), Shiva Kasiviswanathan (Samsung Research)
|— I Know That Person: Generative Full Body and Face De-Identification of People in Images|
Karla Brkic (University of Zagreb), Ivan Sikiric (Mireo), Tomislav Hrkac, Zoran Kalafatic (University of Zagreb)
|— Protecting Visual Secrets using Adversarial Nets|
Nisarg Raval, Ashwin Machanavajjhala, Landon Cox (Duke University)
|— Cartooning for Enhanced Privacy in Lifelogging and Streaming Videos|
Eman Hassan, Rakibul Hasan, Patrick Shaffer, David Crandall, Apu Kapadia (Indiana University)
|— Blur vs. Block: Investigating the Effectiveness of Privacy-Enhancing Obfuscation for Images|
Yifang Li, Nishant Vishwamitra, Bart Knijnenburg, Hongxin Hu, Kelly Caine (Clemson University)
|— ASePPI: Robust Privacy Protection against De-Anonymization attacks|
Natacha Ruchaud, Jean-Luc Dugelay (Eurecom)
|13:30||Invited Talk: Machine Learning and Privacy: Friends or Foes?, Vitaly Shmatikov (Cornell Tech)|
|14:20||Ethics and Education|
|— Trusting the Computer in Computer Vision: A Privacy-Affirming Framework|
Andrew Tzer-Yeu Chen, Morteza Biglari-Abhari, Kevin I-Kai Wang (University of Auckland)
|— Designing a Moral Compass for the Future of Computer Vision using Speculative Analysis|
Michael Skirpan, Tom Yeh (University of Colorado Boulder)
|— Teaching Computer Vision and its Societal Effects: A Look at Privacy and Security Issues from the Students' Perspective|
Melissa Cote, Alexandra Branzan Albu (University of Victoria)
|— Computer Vision Attacks against 3D CAPTCHAs|
Simon Woo (USC/ISI)
|— Filter-Amplifier Network for Detecting Integrated Circuit Packages on Printed Circuit Boards|
Zhenhua Chen, David Crandall (Indiana University), Rob Templeman (NSWC Crane)
|— From Understanding to Controlling Privacy against Automatic Person Identification in Social Media|
Seong Joon Oh, Mario Fritz, Bernt Schiele (Max Planck)
|— Privacy Risks of Using Camera Assisted Tools for People with Visual Impairments|
Taslima Akter, Tousif Ahmed, Kay Connelly, David Crandall, Apu Kapadia (Indiana University)
|— Detection without Recognition for Redaction|
Shagan Sah, Ram Longman, Ameya Shringi (Rochester Institute of Technology), Robert Loce (Conduent), Majid Rabbani, Raymond Ptucha (Rochester Institute of Technology)
|— Privacy-Preserving Human Activity Recognition from Extreme Low Resolution|
Michael Ryoo (Indiana University)
|— Computational Privacy Cameras|
Francesco Pittaluga, Koppal Sanjeev, Aleksandar Zivkovic (University of Florida)
|— Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption|
Ryo Yonetani (University of Tokyo), Vishnu Boddeti (Michigan State), Kris Kitani (Carnegie Mellon University), Yoichi Sato (University of Tokyo)
|— Towards Enhancement of Gender Estimation from Fingerprints|
Emanuela Marasco, Emanuele Plebani, Pegah Karimi, Bojan Cukic (University of North Carolina at Charlotte)
|— Vulnerability of deep learning based gait biometric recognition to adversarial perturbations|
Vinay Uday Prabhu, John Whaley (UnifyID)
|— Smile in the face of adversity much? A print based spoofing attack|
Vinay Uday Prabhu, John Whaley (UnifyID)
|— No need to worry about adversarial examples in object detection in autonomous vehicles|
Jiajun Lu, Hussein Sibai, Evan Fabry, David Forsyth (University of Illinois at Urbana Champaign)
|15:45||Afternoon Break and Poster Session|
|— Assisting Users in a World Full of Cameras: A Privacy-aware Infrastructure for Computer Vision Applications|
Anupam Das, Martin Degeling, Xiaoyou Wang, Junjue Wang, Norman Sadeh, Mahadev Satyanarayanan (Carnegie Mellon University)
|— Caught Red-Handed: Toward Practical Video-based Subsequences Matching in the Presence of Real-World Transformations|
Yi Xu (Snap Inc.), True Price, Fabian Monrose, Jan-Michael Frahm (University of North Carolina at Chapel Hill)
|— Information Hiding in RGB Images using an Improved Matrix Pattern Approach|
Amirfarhad Nilizadeh (University of Central Florida), Wojciech Mazurczyk (Warsaw University of Technology), Cliff Zou, Gary Leavens (University of Central Florida)
|— On the effectiveness of visual watermarks|
Tali Dekel, Michael Rubinstein, Ce Liu, William T. Freeman (Google)
|18:20||Discussion and Concluding Remarks|