Google's AI Watermarks Will Identify Deepfakes
ID: 39284419-d2fa-576f-b91d-77588290afe1
STIX ID: report--39284419-d2fa-576f-b91d-77588290afe1
Feed Name: Dark Reading
Google announced at I/O expanded AI security and provenance measures, extending its SynthID invisible watermarking to AI-generated text and video (in addition to images and audio) and applying these techniques to new models such as Veo and Imagen 3 so generated content can be traced and identified. The company also highlighted AI-assisted red-teaming to find and mitigate problematic outputs and said it will open-source SynthID text watermarking to other vendors.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.