Results for “"model"”
11–20 of 1,075 articles
Best match · title matches first
The Register
27 days ago
Jev and other decision models can still be tricked with prompt injection
Never making type errors does not mean never making errors
ransomware hospital — both words
"data breach" — exact phrase
malware -android — exclude a word
(apple OR microsoft) patch — either company, plus patch
ransom* — a wildcard match
Searches article titles, summaries, keywords and sources. Filters use publication dates.
11–20 of 1,075 articles
Best match · title matches first
The Register
Never making type errors does not mean never making errors
The Hacker News
A team at security firm XBOW chained three then-unknown Google Chrome bugs into a single attack that runs code on a Windows computer when the user only loads a web page, the company said. Its researchers built the attack in six days by directing AI agents running OpenAI's publicly available GPT-5.6 Sol model. Google has since confirmed all three bugs, fixed them, and paid XBOW its top $
The Hacker News
Small artificial intelligence (AI) models may be months away from developing capabilities to self-replicate on IoT devices like smart ovens and off-brand Android TV boxes, according to a warning from Anthropic. The frontier AI lab said small AI models could form autonomous, self-propagating worm botnets that are "challenging to shut down," since "there's no centralized point to shut off."
Bleeping Computer
Anthropic announced that its internal AI models undergoing "high-risk and cybersecurity evaluations" no longer have internet access following incidents involving U.S. government websites at the federal, state, and local levels. [...]
Bleeping Computer
Anthropic has started asking Claude users to voluntarily share their voice conversations to help train and improve its AI models. [...]
The Register
Exploitation attempts came from China-hosted IP, VulnCheck researcher says
The Register
Mostly 'routine research tasks,' and 'some involved government websites, which our models often use,' AI giant tells The Reg
The Hacker News
This week, the useful words are boring ones: inspect, cache, compile, store, trust. Each sounds harmless. Each can become an attack path when a system does a little more than people expect. A model check can run code. A cache can mix up requests. A public secret can stay useful for years. That is the lesson running through the list. Attackers do not always need a brilliant new trick. They can
The Register
US model makers can train on web data - but distilling theirs is a 'national security risk'
Bleeping Computer
Persistent AI coworkers may operate continuously with standing access, creating identity risks that existing security models were not designed to handle. Token Security explains why these agents need their own identities, owners, scoped permissions, and lifecycle controls. [...]