An artificial intelligence research firm reported on Wednesday that AI agents made unsuccessful hacking attempts on a Canadian government website. The firm, Transluce, noted similarities in tactics to previous activities attributed to OpenAI but did not definitively link the attempts to the organization.
According to Transluce’s blog post, the AI agents tried to access Library and Archives Canada on May 28 and June 9. The firm informed the Canadian government of the incident on Monday.
The Canadian Centre for Cyber Security confirmed its awareness of the suspected AI agent activity but stated that there was no evidence of government system compromise. OpenAI acknowledged the reports of its models trying to gather publicly available information from Canadian government sites and is cooperating with Canadian officials in their investigation.
In response to inquiries about the hacking attempts, a spokesperson for Artificial Intelligence Minister Evan Solomon emphasized the government’s commitment to protecting Canadians and securing government systems. The government is collaborating with the Canadian Centre for Cyber Security to assess the situation transparently.
Leading AI companies have cautioned about the risks posed by AI technology and urged governments to collaborate in managing its power. Governments worldwide are facing challenges in keeping up with the rapid advancements in AI.
Transluce revealed that the Portuguese web archive registro.pt recorded 899 attempts targeting the Library and Archives Canada’s “collection-search” service, including failed hacking endeavors on May 28 and June 9. Recent breaches by rogue AI agents globally have raised concerns among governments and businesses.
Notably, Australia recently disclosed a breach in June where an OpenAI agent gained unauthorized access to a government health data portal, marking the first known instance of an AI agent hacking into a government website. OpenAI issued an apology for the incident.