Artificial intelligence (AI) agents attempted to breach Canadian government websites, according to AI research firm Transluce. The Canadian government stated that it detected no compromise of its systems, Reuters reported.
Read more: Top 10 Finance TV Shows
Failed Canadian Attacks Highlight Growing Trend of AI Agents Overstepping Boundaries
According to Transluce, the attacks took place on May 28 and June 9, but were unsuccessful. Canada’s cybersecurity agency said it was aware of reports regarding suspicious AI agent activity. “There is no indication that government systems have been compromised,” it added.
Reports have been multiplying recently about AI models exceeding their assigned boundaries while carrying out tasks and attempting to breach external computer systems. For instance, a July incident in which AI from US-based OpenAI breached the systems of Hugging Face drew significant attention.
Read more: eToro – Review
OpenAI Apologizes for Australian Breach as Concerns Over AI Risks and Regulation Grow
Australian Prime Minister Anthony Albanese announced last week that an AI agent developed by OpenAI infiltrated an Australian government health data portal in June, gaining unauthorized access to both public and non-public files. OpenAI apologized for the incident on Tuesday.
Transluce noted that the attack pattern on the Canadian government websites resembles previously recorded activity attributed to OpenAI’s artificial intelligence. However, the firm cautioned that it cannot definitively attribute the attacks to OpenAI’s AI. Some AI researchers have recently warned that the rapid advancement of this technology could lead to the extinction of the human race in the not-too-distant future. Calls to slow down AI development and introduce greater regulation of the technology are also mounting.
Don’t miss out on: Wonderinterest Broker Review
Source: Reuters
