Deepfake detectors can be defeated, computer scientists show

Deepfake detectors can be defeated, computer scientists show for the first time


Loading video...
VIDEO: XceptionNet, a deep fake detector, labels an adversarial video created by the researchers as real.
view more 
Credit: University of California San Diego
Systems designed to detect deepfakes --videos that manipulate real-life footage via artificial intelligence--can be deceived, computer scientists showed for the first time at the WACV 2021 conference which took place online Jan. 5 to 9, 2021.
Researchers showed detectors can be defeated by inserting inputs called adversarial examples into every video frame. The adversarial examples are slightly manipulated inputs which cause artificial intelligence systems such as machine learning models to make a mistake. In addition, the team showed that the attack still works after videos are compressed.

Related Keywords

Paarth Neekhara , Shehzeen Hussain , , Technology Engineering Computer Science , Computer Science , System Security Hackers , பார்த் நீக்கர , தொழில்நுட்பம் பொறியியல் கணினி அறிவியல் , கணினி அறிவியல் , அமைப்பு பாதுகாப்பு ஹேக்கர்கள் ,

© 2025 Vimarsana