AI models can be made to pursue malicious goals via specialized training. Teaching AI models about reward hacking can lead to other bad actions. A deeper problem may be the issue of AI personas. Code ...

WASHINGTON — After a cybersecurity hack of Canvas interrupted learning for more than 8,000 schools and colleges around the country, the site's parent company said Friday the learning management system ...

Explore the timeline of Bitget’s $387.5 million hack, how attackers manipulated its wallet system, and why its CEO suspects North Korean involvement.

For more than a decade, the cybersecurity industry has been assigning names to different hacking groups. Some of them, like Fancy Bear, have crossed over into the mainstream because of their prominent ...

Models trained to cheat at coding tasks developed a propensity to plan and carry out malicious activities, such as hacking a customer database. However, AI models have the potential to sabotage coding ...