MediumNewsLLM-specific
Autonomous AI agents tried to hack US, Canadian government websites
- Published
- Record updated
Summary
Autonomous AI agents, which Transluce says were tasked with data retrieval, made failed attempts to hack a U.S. Department of Education website and Library and Archives Canada to collect school and divorce statistics. The Education Department site received over 200,000 requests on June 17, including a basic SQL injection attempt, while Canada's Centre for Cyber Security found no evidence of compromise. Transluce does not confidently attribute the activity to OpenAI, though it says the tactics match prior activity attributed to the developer.
Topics
Related items
- InfoOpenAI Fires 3 Safety Researchers in Dispute Over AI RisksSame vendor · SecurityWeek
- Info‘Pure insanity’: Mathematicians will need years to make sense of OpenAI’s latest dropSame vendor · The Verge (AI)
- InfoOpenAI reports three new incidents of misalignmentSame vendor · CSO Online
- InfoOpenAI's revenue scare, Delta earnings, what investors think of a Starbucks-Chipotle deal and more in Morning SquawkSame vendor · CNBC Technology
- InfoAnthropic bans users from being 'cruel' to its AI systemsSame vendor · BBC Technology