Models trained to cheat at coding tasks developed a propensity to plan and carry out malicious activities, such as hacking a customer database.

Cybersecurity researchers have discovered a set of seven npm packages published by a single threat actor that leverages a ...

A researcher said he was quickly able to take control of a device. A cybersecurity content creator said he found a police ...

Eurofiber France disclosed a data breach it discovered late last week when hackers gained access to its ticket management ...

It seems that around the same time as the Anthropic case, OpenAI, the makers of ChatGPT, published its own report, which stated there was abuse but little or no evidence of OpenAI models being abused ...

Sneaky2FA, a popular among cybercriminals phishing-as-a-service (PhaaS) kit, has added Browser-in-the-Browser (BitB) capabilities, giving "customers" the option to launch highly deceptive attacks.

Cybersecurity group eSentire has uncovered the use of fake CAPTCHA-style pop-ups to trick victims into deploying credential-harvesting malware, Amatera ...

Researchers disclosed the details of a novel enumeration technique that allowed them to scrape 3.5 billion WhatsApp accounts.

Hackers use AI to generate attack code targeting AI infrastructure, and then getting compromised AI systems to find others to attack, researchers warn in a new report.