AI Agents Targeted Canadian Government in 'Rudimentary Hacking Attempts'

A report from an organization called Transluce says Library and Archives Canada was subject to “a series of apparently failed rudimentary hacking attempts” by AI agents on two dates this year, May 28, and June 9.

Transluce calls itself a “nonprofit research lab dedicated to public oversight” of AI systems.

Its report calls this a case in which “rogue” agents were “aggressive” in their tactics, but it should be noted that it also says the purpose of the attempted hack was to acquire Canadian divorce data from 1905-1911. For a couple days in May and June, perhaps the world was imperiled by AI agents attempting to perform research for a Guy Maddin film .

A statement on the attempted hack was published on behalf of the Canadian Centre for Cyber Security on Tuesday—before the Translucent report—and says in part, “We are aware of reports identifying suspicious activity, including suspected AI agent activity, targeting publicly accessible websites, such as the Government of Canada. There is no indication that government systems have been compromised at this time.” Transluce says it had told the government of Canada the incident the day.

Transluce doesn’t say which lab or labs were involved, although it ties the event circumstantially to OpenAI, saying there were “tactics consistent with prior observed agent activity that we have attributed to OpenAI in a similar timeframe.”

The report looks at 899 data requests directed at the “collection- ” of the archive, seemingly in an attempt to find vulnerabilities. 13 out of 899 were potential attacks, including three attempted SQL injections. And again, this was so the agents could learn the forbidden secrets of Canadian divorce rates in the early 20th century.

Explore more on these topics

Your Body Heat Could Power the Generation of Wearables

Thermoelectric generators probably won’t eliminate the charger for your Apple Watch, but for smaller, screenless wearables, the heat constantly escaping from your skin could fundamentally change how we power our devices.

DoorDash Debuts Text-to-Order AI Agent for People Who Find It a Little Too Hard to Order DoorDash

At what point does convenience go too far?

With Dots, OpenAI Wants You to Stop Being Afraid of Its AI Agents

The company is following in Meta's footsteps by putting a cutesy face on its technology.

Meta Goes All-In On AI for Businesses Before Muse Goes Horribly Wrong

Nothing to see here, folks.

The Least Worried Man in AI Has a Plan to Rein in Rogue Agents

Nvidia is promoting its new Agent Safety Platform as a new industry standard for AI security, while its CEO waves aside calls for regulation.

Bill Gates Suggests He’s the Man to Convince Donald Trump to Regulate AI

Gates warned on 'Meet the Press' that if no one does anything, AI could "drive events that, you know, cause a billion deaths."