The 2026 U.S. midterm campaigns are the first in which AI-generated political ads are regularly appearing on people’s televisions and social media feeds.

We are researchers who have been studying political advertising through the Wesleyan Media Project since 2010. This election cycle – using data from media reports, student coders and AdImpact, a firm that tracks political ad spending – we’ve tracked about US$80 million in spending on almost 170 unique ads that use AI.

What we found has surprised us: AI use spans from hyperrealistic deepfakes to subtle enhancements; Republican sponsors – both candidates and interest groups – are much more likely to use AI than are Democratic sponsors; and, thanks to a patchwork of state legislation, many of these ads do not disclose the use of AI at all.

From deepfakes to subtle edits

An assortment of politicians and watchdog groups have expressed concern about campaigns using generative AI to produce deepfakes – synthetic videos showing people doing things they did not do – that might deceive voters.

We’ve noticed several ads containing hyperrealistic deepfakes of famous politicians, including Donald Trump, Nancy Pelosi, Barack Obama, Kamala Harris and Alexandria Ocasio-Cortez. Ocasio-Cortez, in particular, is a favorite among Republican advertisers, appearing in at least five ads.

We’ve seen deepfakes in which a Republican Senate candidate from Louisiana drives a school bus full of undocumented........

© The Conversation