Giovanni Vigna and Dawn Song were interviewed for an article in The Atlantic by Matteo Wong titled "Chatbots are Becoming Really, Really Good Criminals."
Opening with a description of a cybersecurity incident at Anthropic, Wong's article takes input from Vigna, Song and other leaders in cybersecurity to describe what he calls an AI hacking arms race: "The better attackers get at using AI models, and the better the technology itself becomes, the harder intrusions will be to guard against. Then again, AI products that uncover new security flaws could also help patch those bugs. (And then those AI tools could be used by hackers to find security flaws in those patches. And so on.)"
Wong also references one of Dr. Song's ACTION-related experiments at UC Berkeley called CyberGym where researchers used AI agents to identify new security holes in a group of public codebases.
Read the complete article at theatlantic.com. Note that you will be asked to log in to view the entire article.