AI Anonymization

See Related Papers and Related Projects:
Semantic Meaning & Analysis   AI Modeling Thought & Language   AI Cognitive Creativity
Sensing Humans (Bio/Brain/Face/Movement/VR)   AI Ethics: Gender   AI Ethics: Climate

Researchers: Steve DiPaola, Vanessa Utz, Nilay Ozge Yalcin

The Research: Bringing together an interdisciplinary team, we have researched and created a wholly new AI technique to anonymize interview subjects and scenes in regular and 360 videos. Our goal was to create a technique that would be much better at conveying emotional and knowledge information than current anonymization techniques. Our studies comparing our AI painterly emotional techniques to the best of the standard pixelization techniques, show viewers watched longer, empathized with the subject more and were more engaged. We have now demoed our work to the NY Times, The BBC, and The Washington Post with the hope of bringing this system to the general public to continue our labs goal of AI for social good.

See main site of the project at aipaint360.org

See samples of the work in the videos below:

**Video 1:** Sample of VR anonymization for journalistic purposes.

**Video 2:** Demo of facial recognition system to track emotional state of subjects.

**Video 3:** Sample 1 of Standard vs AI anonymization tool.

**Video 4:** Sample 2 of Standard vs AI anonymization tool.

------ PAPERS: AI Anonymization ------

See main site at aipaint360.org

Embodied interactions with a sufi dhikr ritual; negotiating privacy and transmission of intangible cultural heritage in virtual sama by Kadir A; Hennessy K; Yalcin ON; DiPaola S – Conference – British Computer Society. pp. 365-372 Best Paper Award
Electronic Visualisation and the Arts (EVA) (2017)