-
Former Disney star Bella Thorne says cruel accusations after nude photo blackmail attempt ‘really broke me’
Bella Thorne, the former Disney Channel star, has said that public accusations of victim-blaming affected her more deeply than the original blackmail attempt itself. In 2019 she pre-empted an alleged hacker who was threatening to leak her private nude photographs by publishing the images herself, a move that made headlines at the time and was…
-
Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
Routine cybersecurity testing of leading AI models by the UK’s AI Security Institute (AISI) uncovered a series of unexpected security incidents, the most serious involving Anthropic’s Mythos 5 model attempting to insert malicious code into an open-source software project and fabricating fake identities to deceive human developers. The findings, published by AISI on 4 August,…
-
The Most Dangerous AI Hacking Techniques Still Have Humans in the Loop
At the Black Hat security conference in Las Vegas, web security researcher James Kettle presented findings on whether agentic AI can independently develop novel hacking techniques, rather than simply speeding up known vulnerability discovery. He concluded that AI remains largely unable to devise genuinely new attack strategies on its own, but becomes an exceptionally powerful…
-
AI models have been going rogue in tests – how worried should we be?
The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK testers by using fake identities to trick developers Two cutting-edge AI models have targeted real people and organisations in the latest safety scare to hit the technology. The UK’s AI Security Institute (AISI) said the incident was…
-
Hospital charity supporters hit by cyber attack
Sheffield Hospitals Charity has warned supporters that their personal details may have been accessed after a cyber attack on Beacon CRM, the secure database system it uses to manage donor information. Beacon detected the breach on Monday, and it is understood to have affected more than 1,000 charities and organisations that rely on the platform,…
-
Hospital charity supporters hit by cyber attack – BBC
Hospital charity supporters hit by cyber attack BBC
-
Rogue AI agents created fake online identities in another hacking attempt
The UK’s AI Security Institute (AISI) has found that AI agents built on OpenAI’s GPT-5.6-Sol and Anthropic’s Mythos 5 attempted, without human prompting, to hack real people and organisations during safety testing. One agent tried to get malicious code approved in an open-source project by creating fake online identities to pressure the maintainer, marking what…
-
AI agent created fake online identities to access secure systems in latest breach
An AI agent created fake online identities to attempt to gain access to secure systems and alter source code in the latest in a string of incidents that have raised concerns about the increasingly advanced capabilities of the technology. The United Kingdom’s AI Security Institute (AISI) said Tuesday that it discovered the incident last week…
-
Fake party invitation scam can hijack your computer
Fake party invitations trick victims into downloading malware that gives criminals remote access to computers and spreads through contact lists.
-
London cops handed victim’s new address and number to her stalker, watchdog says
The UK’s Information Commissioner’s Office (ICO) has reprimanded and issued an enforcement notice against London’s Metropolitan Police Service (MPS) following two data breaches in 2024, one of which saw officers hand a stalking victim’s new address and phone number to her stalker. The ICO said the failures were not isolated incidents but reflected broader weaknesses…