Photo credit: The Sun
Researcher and Computer Science PhD student Giannis Daras has uncovered a secret language that DALL·E 2, a cutting edge text-to-image artificial intelligence generator, has created. It’s believed that DALL·E 2 makes up its own words to make sense of the images it generates. Daras then fed these words back to the system and apparently, the AI understood exactly what it was reading.
Daras thinks that this is a big security hole for the text-to-image generator, as it could prompt backdoor adversarial attacks or provide ways to circumvent filter. As of now, Natural Language Processing systems filter text prompts that violate the policy rules and gibberish prompts may be eventually used by attackers to bypass these filters. However, this still isn’t as cool as the AI-generated Gran Theft Auto V.
- Powerful Productivity: AMD Ryzen 3 3350U delivers desktop-class performance and amazing battery life in a slim notebook. With Precision Boost, get up...
- Maximized Visuals: See even more on the stunning 15.6" Full HD display with 82.58% screen-to-body, 16:9 aspect ratio and narrow bezels
- Backlit Keyboard and Fingerprint Reader: Biometric fingerprint reader and Windows Hello sign-in options help keep your Acer PC secure
Another example: ‘Two whales talking about food, with subtitles’. We get an image with the text ‘Wa ch zod rea’ written on it. Apparently, the whales are actually talking about their food in the DALLE-2 language,” said the researcher.
And look, prompting DALL-E with "Evve waeles" gave me a picture of a delicious dessert!
But also – some footballers, some animals and a kettle?
(12/15) pic.twitter.com/jncHq0W13Q
— Benjamin Hilton (@benjamin_hilton) May 31, 2022