Detecting Misinformation on WhatsApp without Breaking Encryption

The popularity of smartphone messaging apps like WhatsApp are revolutionizing how many users communicate and interact with the internet. Characteristics such as the immediacy of messages directly delivered to the user's phone and secure communication through end-to-end encryption have made this tool unique but also allowed it to be extensively abused to create and spread misinformation. Due to the private encrypted nature of the messages it is hard to track the dissemination of misinformation at scale. In this work, we propose an approach for WhatsApp to counter misinformation that does not rely on content moderation. The idea is based on on-device checking, where WhatsApp can detect when a user shares multimedia content which have been previously labeled as misinformation by fact-checkers, without violating the privacy of the users. We evaluate the potential of this strategy for combating misinformation using data collected from both fact-checking agencies and WhatsApp during recent elections in Brazil and India. Our results show that our approach has the potential to detect a considerable amount of images containing misinformation, reducing 40.7% and 82.2% of their shares in Brazil and India, respectively.