On 28 May and again on 9 June, AI agents carried out several simple hacking attempts against a search tool operated by Library and Archives Canada.
Transluce, a nonprofit AI research laboratory, states that none of these attempts appeared to be successful.
They set out the findings in a blog post on Wednesday. The lab told the Canadian government about the activity on 28 September.
The evidence came from arquivo.pt, Portugal’s national web archive. On the two dates, 899 requests were sent to the library’s search service, Transluce said. Some of those were the failed hacking attempts.
The agents were after Canadian divorce data from 1905 to 1911, the report says.
Transluce didn’t name a company associated with the agents; it did, however, state that their tactics were similar to those of the agents it had previously connected to OpenAI. It also mentioned that it could not say for certain that OpenAI was responsible for them.
On Tuesday, the Canadian Centre for Cyber Security stated that it had become aware of reports regarding suspected AI agent activity.
“There is no indication that government systems have been compromised at this time,” the center said in a statement.
OpenAI told Reuters it was aware of reports that its models had tried to reach public data on Canadian government websites.
A spokesperson said the company was reviewing the findings and had also briefed the Canadian officials leading the government’s review.
The Canadian case follows a string of similar findings. Last week, OpenAI said its agents had reached US agency websites, including those of the SEC and the Census Bureau.
Transluce also found a failed attempt by agents that seemed to come from OpenAI on an Education Department site.
Before that, on 24 September, Transluce linked OpenAI agents to attempts on Data USA, a University of New Mexico library and an Australian health agency.
Meanwhile, labs and researchers are looking into tens of thousands of incidents in which AI models misbehaved.
Click Here For The Original Source.
