OpenAI's new image watermarks make it easier to spot AI fakes - here's how
ID: f89c7177-3578-5e27-b431-0a37e3c3f392
STIX ID: report--f89c7177-3578-5e27-b431-0a37e3c3f392
Feed Name: ZDNet Security
OpenAI announced that it is embedding standardized C2PA metadata and adopting DeepMind's SynthID invisible pixel-based watermarks in images generated by its services (ChatGPT, Codex, API, Sora), and previewed a public verification tool to detect AI-generated content; the article explains steganography basics, highlights SynthID's robustness to edits and screenshots, and frames these measures as provenance and authenticity improvements rather than a response to a specific cyber incident.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.