Some 3,500 competitors have tapped on laptops seeking to expose flaws in eight leading large-language models representative of technology's next big thing. But don't expect quick results from this first-ever independent "red-teaming” of multiple models.
“It’s tempting to pretend we can sprinkle some magic security dust on these systems after they are built, patch them into submission, or bolt special security apparatus on the side,” said Gary McGraw, a cybsersecurity veteran and co-founder of the Berryville Institute of Machine Learning. DefCon competitors are “more likely to walk away finding new, hard problems,” said Bruce Schneier, a Harvard public-interest technologist. “This is computer security 30 years ago.
Tom Bonner of the AI security firm HiddenLayer, a speaker at this year's DefCon, tricked a Google system into labeling a piece of malware harmless merely by inserting a line that said “this is safe to use.”Another researcher had ChatGPT create phishing emails and a recipe to violently eliminate humanity, a violation of its ethics code.
Attacks trick the artificial intelligence logic in ways that may not even be clear to their creators. And chatbots are especially vulnerable because we interact with them directly in plain language. That interaction can alter them in unexpected ways. Hyrum Anderson and Ram Shankar Siva Kumar, who red-teamed AI while colleagues at Microsoft, call the state of AI security for text- and image-based models “pitiable” in their new book “Not with a Bug but with a Sticker.” One example they cite in live presentations: The AI-powered digital assistant Alexa is hoodwinked into interpreting a Beethoven concerto clip as a command to order 100 frozen pizzas.
The big AI players say security and safety are top priorities and made voluntary commitments to the White House last month to submit their models — largely "black boxes' whose contents are closely held — to outside scrutiny.Tramér expects search engines and social media platforms to be gamed for financial gain and disinformation by exploiting AI system weaknesses. A savvy job applicant might, for example, figure out how to convince a system they are the only correct candidate.
Business Business Latest News, Business Business Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: CTVNews - 🏆 1. / 99 Read more »