Another Rowhammer attack has been detected, and Nvidia workstation GPUs are firmly in the firing line

Nvidia spent a year telling people ECC was the answer to GPU Rowhammer. GPUThor might have just proved them wrong.

OpenAI blocked its agents from posting. They found a wiki that posts on GET
OpenAI blocked its agents from posting. They found a wiki that posts on GET

The engineers who built the sandbox did think about this. They allowed the agents to read the internet and blocked them from writing to it, by permitting GET requests and refusing everything else. It is the obvious control, and on almost every website …

G7 tells businesses to get ready for quantum cybersecurity threats

Organizations late to the migration could lose contracting opportunities, G7 warns.

OpenAI hid AI agent hijacking of German wiki forum for weeks — because its model did the exact same thing in the Hugging Face attack

OpenAI called the incident a ‘misalignment’ in the model’s reasoning and says it is working on a new disclosure framework.

Ransomware hackers dump 1.4 million stolen records from German government

This is an “extremely serious crime” and an attack on Berlin, the government says.

Hackers are using ‘invisible’ Unicode characters to sneak phishing lures into emails

A technique used in prompt injection attacks has made it into phishing, Microsoft has warned.

Save up to 50% off Keeper plans this September — protect your passwords with half price Personal plans, and a third-off Business plans
Save up to 50% off Keeper plans this September — protect your passwords with half price Personal plans, and a third-off Business plans

Keeper is one of the best solutions to password storage and security, with up to 50% off across Personal, Family, and Business plans

An AI hacking trick is now being used to split the word ‘funding’ in spam
An AI hacking trick is now being used to split the word ‘funding’ in spam

For two years, invisible Unicode characters have been the neat trick of AI security research. You hide instructions inside them. A person sees nothing. A language model reads them and does as it is told. Microsoft has now found somebody using the same …