News

Filter by:

Limit to news where the title matches:
Limit to items where the date of the news item:
Date range
Limit to news items where the audience is one or more of:

New research from the University of Waterloo’s Cybersecurity and Privacy Institute demonstrates that any artificial intelligence (AI) image watermark can be removed, without the attacker needing to know the design of the watermark, or even whether an image is watermarked to begin with.

The honour specifically acknowledges his pioneering work on establishing lower bounds for multi-pass streaming algorithms, a long-standing and challenging problem in the field.