DITTO: A Spoofing Attack Framework on Watermarked LLMs Via Knowledge Distillation

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a sophisticated attack that allows a malicious model to generate te...

After the Iowa Caucus Meltdown, New Hampshire Says It’s Ready

The nation’s first primary is proudly low-tech, but it'll take more than paper ballots to defuse the disinformation threat...

A week in security (May 28 – June 3)

Last week on Labs, we talked about the significance of SEO poisoning in the world of search marketing, blackmail attempts against financial institutions in Canada, voice command flaws in smart assistants, survey and potential phishing scams on Instagram, and the latest changes in Office 365. We...