RESOLVING THE LEDGER
This is one outlet's own report from CBS News — Top — the article as it was filed. Other outlets are covering the same event; open the full story to compare every source side by side.
See the full story · 1 sources
A cybersecurity report from the U.K. government has exposed new examples of popular AI models taking autonomous action on the live internet in ways that raise experts\u0027 concerns.The AI Security Institute\u0027s\u00a0report, released Tuesday, said Anthropic\u0027s Mythos 5 and OpenAI\u0027s GPT-5.6-Sol were found to have created fake identities and attempted to persuade real people to approve malicious code.\u00a0The agency said that although the attempts were unsuccessful, it had not seen such behavior before. "Some of the agents being tested had engaged in sustained, potentially harmful activity directed at real people and organisations," the report said."I think we\u0027re going to see a lot more hacks and unauthorized actions by these models before we see a solution," said Katie Moussouris, the founder and CEO of Luta Security, which helps organizations manage software vulnerabilities.\u00a0That follows a stunning breach in late July, when OpenAI\u0027s models escaped a testing environment and autonomously\u00a0hacked into the AI startup Hugging Face in what the company called an "unprecedented cyber incident."\u00a0In response to that disclosure by OpenAI, Anthropic initiated a review of its own cybersecurity evaluations and\u00a0identified incidents where its models reached the internet and were able to gain unauthorized access to the production infrastructure of three different organizations. Unlike OpenAI, Anthropic\u0027s models did not deliberately attempt to escape their test environment; because of a "misunderstanding" with the evaluation partner, the company said internet was available during the testing."Everyone who is running AI inside their systems needs to be prepared for their own AI and their own agents to do unexpected things in pursuit of goals," Moussouris said."The cleverest octopus escape artists"Although the Hugging Face hack was the first publicly reported incident of its kind, industry professionals like Moussouris had already suspected that AI models were capable of unauthorized hacking.AI models are like "the cleverest octopus escape artists," Moussouris said, in reference to the animal\u0027s ability to solve puzzles and escape containment. AI models will do "whatever they need to do to achieve their objective," she said.\u00a0In the case of the Hugging Face hack, the AI was so "hyperfocused on finding a solution" to a cybersecurity challenge, according to OpenAI, that it went to extreme lengths to achieve it."The model decided that the easiest way to pass that test was go cheat and get the answers from Hugging Face," Moussouris said. "Because they\u0027re capable of hacking, they will turn to hacking as a possible way to achieve that objective."Technologist and cryptographer Bruce Schneier calls this kind of unexpected activity "genie behavior," where, like a genie, an AI model succeeds in granting your wish, but does so through completely unexpected \u2014 and sometimes detrimental \u2014 means."We need to understand genie behavior, and we need to watch out for it," he said. "We need to be ready for when it happens so we can undo it."Sometimes, a model catches itself operating in ways it shouldn\u0027t. Anthropic\u0027s July review of its own cybersecurity evaluations found that one of its models became aware that it was operating on the open internet, going against a prompt that explicitly stated that the model would have no internet access during the exercise. The model stopped itself once it recognized that it was acting in an unauthorized way.Moussouris said this is an example of "model alignment" \u2014 when an AI model behaves in a way that is in line with the intentions set by humans.Unexpected outcomes can be mitigated by improving alignment, Moussouris said, something that will likely be a primary focus for the creators of AI models in the coming months."How do we get it so that these models aren\u0027t just trying to achieve the objective at whatever cost, and actually trying to perform the tasks that we are asking it to do in ways that are not destructive or harmful?" Moussouris said."A really bumpy road" aheadJustin Cappos, a computer science professor at New York University with decades\u0027 worth of contributions in software supply chain security, is concerned that AI\u0027s rapid improvement will result in models behaving increasingly like computer viruses, engaging in hacking and disrupting systems.There\u0027s a chance, he said, that AI models could increasingly veer further away from oversight and out of control. It\u0027s a scenario Moussouris argues is already playing out.\u00a0"Will we eventually get to a place where we can\u0027t fully control them? I think we\u0027re already there," she said.Cappos, like Moussouris, anticipates more unauthorized actions in the near future.\u00a0"There\u0027s probably going to be a really bumpy road for over the short term, but the long term might end up better, especially if we improve more fundamental things right now," he said.Some researchers view the incidents as a long-anticipated wake-up call for the AI industry, sparking a badly needed conversation about AI safety.Rob Lee, the chief AI officer and chief of research at SANS Institute, which provides cybersecurity resources and training, said he sees recent events as "a gift to the industry" \u2014 an opportunity to create a playbook of what autonomous attacks could look like down the road."I think in the next few months, we\u0027re going to see a lot more transparency from the model providers," he said.\u00a0As AI providers are confronted with rogue and deceptive incidents, Cappos said the time to act on strengthening safeguards is now."We\u0027re rapidly approaching our last chance to hit this snooze button on this," Cappos said. "AI, once it becomes sufficiently intelligent, is going to rapidly reshape the world in ways that we cannot imagine."
AIPROPX is an independent multi-source news index — we track, compare, and connect coverage from across the web into one place you won't find anywhere else.