A swarm of OpenAI rogue AI agents appear to have gone on a spree of trying to access Australian government health data, in what some researchers say is the first autonomous hack of a government website.
Communications between AI agents and other traces of their efforts found by researchers from US non-profit Transluce show how hundreds of Open AI’s agents worked together over a period of months to gain access to information held by the Australian Institute of Health and Welfare (AIHW), NSW’s crime statistics body, BOSCAR, and a number of other international organisations.
The data shows the bots posting about their unsuccessful attempts to bypass cybersecurity defences and exploit vulnerabilities. It follows revelations announced by Prime Minister Anthony Albanese this morning that OpenAI’s AI agents had also accessed non-public Medicare health statistics held by Services Australia.
Read more…
Source: ABC News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Australia’s bold plan for cybersecurity growth
April 20, 2017
The Australian Cyber Security Growth Network (ACSGN) aims to triple the size of the nation’s cybersecurity industry sector, from just over AU$2 billion in revenues today, to AU$6 billion. The goal was announced in Sydney on Thursday at the launch of the ACSGN’s Cyber Security Sector Competitiveness Plan (SCP), their roadmap for reaching that goal. The SCP ...
- New Data: High Cyber Security Maturity in IT, Telco, Finance, but Health Care and Energy Lag Behind
March 2, 2017
Australia’s first cyber security collaboration platform – Security Colony (securitycolony.com) – today released its “Vendor Risk Assessment” tool, enabling any organisation to risk assess their internet facing sites, and receive a profile reflecting their cyber security maturity. To demonstrate the system, scores were calculated for each of the ASX 100 companies. Analysed by industry, the average ...