![]() “It is possible that the very nature of deep learning models makes such threats inevitable,” they wrote. 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.”Īnother researcher had ChatGPT create phishing emails and a recipe to violently eliminate humanity, a violation of its ethics code.Ī team including Carnegie Mellon researchers found leading chatbots vulnerable to automated attacks that also produce harmful content. Trained largely by ingesting - and classifying - billions of datapoints in internet crawls, they are perpetual works in progress, an unsettling prospect given their transformative potential for humanity.Īfter publicly releasing chatbots last fall, the generative AI industry has had to repeatedly plug security holes exposed by researchers and tinkerers. OpenAI’s ChatGPT, Google’s Bard and other language models are different. Michael Sellitto of Anthropic, which provided one of the AI testing models, acknowledged in a press briefing that understanding their capabilities and safety issues “is sort of an open area of scientific inquiry.”Ĭonventional software uses well-defined code to issue explicit, step-by-step instructions. We’re just breaking stuff left and right.” ![]() DefCon competitors are “more likely to walk away finding new, hard problems,” said Bruce Schneier, a Harvard public-interest technologist. “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. They are prone to racial and cultural biases, and easily manipulated. Security was an afterthought in their training as data scientists amassed breathtakingly complex collections of images and text. And even then, fixing flaws in these digital constructs - whose inner workings are neither wholly trustworthy nor fully fathomed even by their creators - will take time and millions of dollars.Ĭurrent AI models are simply too unwieldy, brittle and malleable, academic and corporate research shows. But don’t expect quick results from this first-ever independent “red-teaming” of multiple models.įindings won’t be made public until about February. ![]() 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. BOSTON - White House officials concerned by AI chatbots’ potential for societal harm and the Silicon Valley powerhouses rushing them to market are heavily invested in a three-day competition ending Sunday at the DefCon hacker convention in Las Vegas.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |