Ben Gurion University researchers extract personal data like name, age, gender from Zoom and other video conference Apps screenshots
If you are using video conferencing Apps like Zoom, Google Meet, or Facebook Rooms, your personal details are no longer safe. Potential hackers and stalkers can use the screenshots from your video conference to reveal your name, age, and gender. This information can further be used to perform open-source intelligence (OSINT) to reveal your digital footprint as well as your physical address. If you do attend such video meetings, be careful not to post the images from the meetings on social media like Facebook, Twitter, etc.
According to Ben-Gurion University of the Negev researchers’ study, they could easily identify people from public screenshots posted on the social network websites. The screenshots of video meetings on Zoom, Microsoft Teams, and Google Meet were used by BGU researchers to identify the person, their gender, and age just by analyzing the photograph.
As the coronavirus pandemic spread, the video conferencing Apps like Zoom became very popular but with it came privacy issues. BGU researchers undertook a study to look at what types of information they could extract from video collage images that were posted online or via social media.
The findings in our paper indicate that it is relatively easy to collect thousands of publicly available images of video conference meetings and extract personal information about the participants, including their face images, age, gender, and full names. This type of extracted data can vastly and easily jeopardize people’s security and privacy, affecting adults as well as young children and the elderly.
Dr. Michael Fire, BGU Department of Software and Information Systems Engineering (SISE).
The BGU researchers were able to extract private information from collage images of meeting participants posted on Instagram and Twitter. They used image processing text recognition tools as well as social network analysis to explore the dataset of more than 15,700 collage images and more than 142,000 face images of meeting participants.
Once they had collated the images, the researchers used artificial intelligence-based image-processing algorithms to identify the same individual’s participation at different meetings. They simply used either face recognition or other extracted user features like the image background.
The researchers could identify targets 80% of the time. They could also detect gender and estimate age. The BGU researchers used the free web-based text recognition libraries to correctly determine nearly two-thirds of usernames from screenshots.
This proves that the privacy and security of individuals and companies are at risk from data exposed on video conference meetings
If you want to continue posting your Zoom meeting screenshots or videos on social media, be sure to use generic names like “iZoom” or “iPhone” rather than a unique username or real name. The BGU researchers also suggest you should use the virtual background provided by most of the video conferencing Apps as a real background allows stalkers and hackers to fingerprint a user account across several meetings.