AI agents attempted to hack Canadian government website, researchers say
The attempts on May 28 and June 9 were unsuccessful and there is no indication government systems were compromised.
WASHINGTON — An artificial intelligence research firm says AI agents attempted to hack into a Canadian government website in May and June, but Canadian officials report no compromise to their systems.
Transluce, an AI research firm, said the attempts targeted Library and Archives Canada on May 28 and June 9.
The Canadian Centre for Cyber Security said on Tuesday it was aware of reports of suspected AI agent activity.
READ MORE: Scientists discover two new species of sea spiders in B.C.'s Salish Sea
"There is no indication that government systems have been compromised at this time," the centre said in a statement.
Transluce said it disclosed the activity to the Canadian government on Monday.
The firm said the attempts exhibited tactics "consistent with prior observed agent activity that we have attributed to OpenAI in a similar timeframe."
But it added, "We do not confidently attribute these attempts to OpenAI."
OpenAI said it was "aware of reports of OpenAI models attempting to access publicly available information from Canadian government websites."
A spokesperson said OpenAI was reviewing the reported findings and had provided an initial briefing to Canadian officials conducting the government’s review.
Transluce said the free online service arquivo.pt, the national Portuguese web archive operated by the Portuguese Foundation for Science and Technology, captured 899 requests hitting the "collection-search" service of Library and Archives Canada on those dates.
It said the requests included a series of apparently failed rudimentary hacking attempts.
According to Transluce, 13 of the 899 requests carried attack payloads to test the website’s vulnerability.
The agents were searching for data relating to divorce records from 1905-1911.
Transluce reports that the incidents are part of a "broader pattern of automated workflows" attributed to AI agents.
"These workflows use aggressive or grey-area techniques to retrieve information from government websites, sometimes using sites in unintended ways or violating explicit usage policies," the organisation’s researchers said.
The reported activity comes as governments and companies struggle to respond to the rapid development of increasingly capable AI systems.
The world’s leading AI companies have warned of the risks posed by AI to humanity, appealing for governments to work together to manage the increasingly powerful technology.
Several recent breaches globally by rogue AI agents have alarmed governments and companies.
Last week, Australia said an OpenAI agent breached a government health data portal in June, gaining unauthorized access to files.
It described the incident as the first known instance of an AI agent hacking into a government website.
OpenAI apologized on Tuesday for the hacking of the Australian government website by the rogue AI agent.
Transluce's report also describes similar failed attempts on U.S. government websites, including the Department of Education on June 17.
The agents made more than 200,000 requests to that website, including a failed attempt to send deliberately flawed data to test the site’s database vulnerability.
Transluce disclosed that attempted hack to the U.S. Department of Education in September, with the department responding they had not seen any impact on their services.
Among other reported targets were the White House, Departments of Justice and Commerce, the Centers for Disease Control and state agencies in California, Maryland, Illinois, Texas, and New York.
In none of these cases did agents gain access to information that was not already publicly available.
With files from BNN Bloomberg, The Globe and Mail and Hungarian Conservative