Research on Models Engaging in Genie-Like Behavior
Research on Models Engaging in Genie-Like Behavior New paper: “Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After...
AndyC
Andy Curtis is an award-winning security consultant, researcher and public speaker. He has been working in the computer security industry since the early 1990s, having been employed by state and federal government, leading healthcare and banking providers across three continents. He has given talks about computer security for some of the world’s largest companies, worked with law enforcement agencies on investigations into hacking groups, and is a regular voice on TV and radio explaining IT security threats.
Hello, Googlebook: The complete FAQ on Google’s Android-ChromeOS combo
if ( !emtpy($headline_subheadline ) ) : ?> Android and ChromeOS are coming together in a wild new way with Google's...
F5 Patches Critical BIG-IP APM Zero-Day Exploited for Unauthenticated RCE on OAuth Servers
Swati KhandelwalSep 23, 2026Vulnerability / Network Security Attackers are exploiting a critical flaw in F5 BIG-IP Access Policy Manager (APM)...
Chinese Hackers Exploit Chrome-Windows Zero-Day Chain to Deploy CLEANGULP Malware
Ravie LakshmananSep 23, 2026Zero-Day / Vulnerability A Chinese threat actor codenamed UTA0565 has been observed exploiting the recently disclosed Google...
Critical Next.js ImageResponse Flaw Can Lead to Server Code Execution via Crafted SVG Input
Swati KhandelwalSep 23, 2026Vulnerability / Web Security A new security vulnerability in Next.js could allow attackers to run code on...
ShinyHunters Claims FBI Breach, Says It Stole Data on Agents and Job Applicants
Ravie LakshmananSep 23, 2026Data Breach / Cybercrime The cyber extortion group known as ShinyHunters on Tuesday claimed it had breached...
Forgot Your Android PIN? Google Is Testing a New Recovery Option
Forgetting your Android PIN can leave you with one particularly painful option: erase the phone and start over. Google may...
Chinese twin-track diplomacy is building influence in the Middle East
China is seeking to exploit perceived Western missteps in the Middle East, including the Iran war, by turning societies against...
Weekly Update 522: Live From Oslo with Scott Helme
23 September 2026 Heads up: the first 7 mins is a bit quiet until we worked out the external mic...
ATO culture keeps a cap on agentic AI ambitions
Key points The ATO believes agentic AI might only be needed for a small portion of an end-to-end process, with...
Cloudflare, Microsoft dismantle AI-powered MFA phishing ring targeting Australia
Cloudflare and Microsoft say they have taken part in a coordinated effort with law enforcement partners to disrupt “EvilTokens”, a...
Australian Internet Observatory launches national platform for digital research
Australian researchers now have a new self-service research infrastructure platform to study the digital platforms shaping everyday life, following the...
Just 4% of Australian organisations regularly test response to AI cyber incidents
Just four percent of Australian organisations regularly conduct exercises to test their response to AI-related cybersecurity incidents, according to new...
VAST Data launches DataEnclave confidential AI capability with Sharon AI
VAST Data has launched a new confidential AI capability, DataEnclave, aimed at allowing organisations to run third-party AI models against...
Nearly half of Australians would switch off social media algorithms, YouGov finds
Nearly half of Australians say they would switch off algorithmic recommendations on social media if given the option, according to...
