Meta has launched Video Seal, a tool designed to address the rising issue of AI-generated deepfakes by embedding imperceptible watermarks into videos. This tool, announced in open-source format, aims to provide a robust solution for identifying AI-generated content while protecting originality. Pierre Fernandez, an AI research scientist at Meta, stated, “We developed Video Seal to provide a more effective video watermarking solution, particularly for detecting AI-generated videos and protecting originality.” The watermarking method is resilient to common edits like blurring, cropping and compression algorithms.
Read more: Meta Removes Over 2 Million Accounts Involved in Scams
Meta plans to encourage its wider adoption by launching the Meta Omni Seal Bench, a public leaderboard to compare the performance of watermarking tools. The company will also host a workshop on watermarking at the upcoming ICLR AI conference. Fernandez emphasized the need for collaboration in the industry, saying, “We hope that more and more AI researchers and developers will integrate some form of watermarking into their work. We want to collaborate with the industry and the academic community to progress faster in the field.” Despite challenges, including proprietary solutions in use, Video Seal represents a significant step in combatting AI-driven misinformation.
Stay tuned to Brandsynario for latest news and updates.