Photo: Sentinel co-founders, Kaspar Peterson (left) and Johannes Tammekänd (right). Photo Credit: Sentinel
Our member United Angels VC
participated in a seed investment round to Estonia-based Sentinel, which is developing a detection platform for identifying synthesized media (aka deepfakes). Together with Unted Angels VC the $1.35 million round included seasoned angel investors — Jaan Tallinn (Skype), Taavet Hinrikus (TransferWise), Ragnar Sass & Martin Henk (Pipedrive).
Sentinel co-founder and CEO Johannes Tammekänd explains that according to their approach it is impossible to detect all deepfakes with only one detection method. „We have multiple layers of defense that if one layer gets breached then there’s a high probability that the adversary will get detected in the next layer,” he adds.Photo Credit: Sentinel
Tammekänd says Sentinel’s platform offers four layers of deepfake defense at this stage: An initial layer based on hashing known examples of in-the-wild deepfakes to check against (and which he says is scalable to “social media platform” level); a second layer comprised of a machine learning model that parses metadata for manipulation; a third that checks for audio changes, looking for synthesized voices, etc; and lastly a technology that analyzes faces “frame by frame” to look for signs of visual manipulation.
“We take input from all of those detection layers and then we finalize the output together as an overall score to have the highest degree of certainty,” he says.
Tammekänd also emphasizes the importance of data in the deepfake arms race — over and above any specific technique. Sentinel’s boast on this front is that it has amassed the “largest” database of in-the-wild deepfakes to train its algorithms on.