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 asks FBI to help find attacker who stole data from millions of users
September 28, 2022
Australian authorities have asked the United States Federal Bureau of Investigation (FBI) to assist with investigations into the data breach at local telco Optus. Attorney general Mark Dreyfus yesterday revealed the FBI was asked to help identify the entities involved in the attack, which saw Optus leak data describing over ten million account holders. Data suspected ...
- Meet Pedro, the police dog sniffing out Canberra’s cybercrime
September 17, 2022
Hold your smartphone up to your nose and take a deep sniff. That’s what Pedro can smell too. Pedro is a technology detector dog for the National Canine Operations unit of the Australian Federal Police (AFP). He and his four-legged peers are tasked with sniffing out laptops, phones, USB sticks and other electronic devices for criminal ...
- China-linked APT40 gang targets wind farms, Australian government
August 31, 2022
Researchers at security company Proofpoint and PricewaterhouseCoopers (PWC) said on Tuesday they had identified a cyber espionage campaign that delivers the ScanBox exploitation framework through a malicious fake Australian news site. The campaign, active from April to June of this year, targeted Australian government agencies, Australian media companies and manufacturers who conduct maintenance on wind turbine ...
- Switching side jobs: Links between ATMZOW JS-sniffer and Hancitor
August 17, 2022
The hacker group ATMZOW and its JavaScript-sniffer became known in 2020, thanks to the Malwarebytes researchers, when the group installed a JS sniffer on a website that was collecting donations for victims of the Australia bushfires. However, based on a specific obfuscation technique used by the group, we can track its activities back to 2015 as ...
- Aoqin Dragon hacking group quietly spied on their targets for 10 years
June 10, 2022
Researchers have discovered a stealthy espionage campaign by a most likely China-backed hacking group that has targeted government, education and telecommunication organizations since 2013. The attackers used a range of techniques to infect targets with malware, such as via malicious Word documents, fake removable devices leading users to malicious folders, and fake antivirus vendor icons that ...
- Australian National Disability Insurance Scheme provider breached and treating its database as compromised
May 31, 2022
CTARS, the makers of a cloud-based client management system used by the Australian National Disability Insurance Scheme (NDIS) as well as disability services, out of home care, and children’s services, has revealed it was breached on May 15 and found the data posted to the dark web a week later. “Although we cannot confirm the details ...