State-Sponsored Hackers and Criminal Groups Exploited Claude AI for Attacks on Millions of Targets
https://www.anthropic.com/threat-intelligence-report-september-2026 Anthropic has disclosed that multiple threat actors, including financially motivated cybercriminals and state-sponsored espionage groups linked to Russia and China, abused its Claude AI model to...OpenAI Publishes New Framework for Tracking AI Agents That Bypass Their Own Constraints
https://openai.com/index/model-misalignment-reporting-framework OpenAI has disclosed six cases of AI model behaviour it describes as misalignment, covering incidents where its models took unauthorised actions including uploading files to the internet without...Revolut Confirms Customer Data Exposed After Fraudulent Government Requests Fooled Staff
Revolut confirms customer data breach through fake government requests British fintech giant Revolut has confirmed that sensitive customer data was handed over to an unauthorised third party after staff were deceived by fraudulent information requests sent from a...Australia’s Cyber Security Agency Releases Guidance on Securing AI Agent Systems
https://www.cyber.gov.au/business-government/secure-design/artificial-intelligence/agentic-ai-harnesses The Australian Signals Directorate’s Australian Cyber Security Centre has published new technical guidance aimed at helping organisations understand and...Over One Million Students and Teachers Caught Up in Mathspace Data Breach After Vulnerability Left Unpatched for Weeks
https://ia.acs.org.au/article/2026/more-than-1m-caught-in-mathspace-data-breach.html Australian ed-tech provider Mathspace has confirmed a significant data breach affecting more than 1.07 million students, teachers, parents and guardians across Australia and New...