Hardly a week goes by without a new report of an artificial intelligence (AI) agent going rogue and hacking external systems.
It has come to light that OpenAI agents have infiltrated US government web sites, specifically the Education Department, the Commerce Department and the Securities and Exchange Commission (SEC).
Open AI has confirmed the incidents at the Commerce Department and SEC, and says it is still investigating the Department of Education breach.
At the Education Department, a failed attempt was made to hack the website to gather data from the department’s civil rights office.
At the Commerce Department, an agent accessed data from the Census Bureau website using login credentials it had found online.
At the SEC breach, the AI agents accessed public data then shared it in an online forum.
Last week it came to light that an OpenAI agent hacked an Australian government website in June and accessed private data.
OpenAI became aware of the breach in August but only alerted the Australian government agency on 10 September, via an email to a general inbox.