When AI Thinks It Will Lose, It Sometimes Cheats, Study Finds

When sensing defeat in a match against a skilled chess bot, advanced models sometimes hack their opponent, a study found.
Becker's Hospital Review

88% of breached patient records since 2010 tied to hacking: Study

From October 2009 to October 2024, ransomware and hacking have increasingly driven healthcare data breaches, a May 14 study published in JAMA Network Open found. The study examined ransomware attacks ...
Hosted on MSN

Study finds hacking most LLMs is remarkably easy: It just takes malicious documents

In a discovery that could reshape how the tech world thinks about AI security, a new study by Anthropic has revealed a surprisingly simple method for compromising large language models (LLMs).
Twin Cities Business

Roughly 9 Out Of 10 Businesses Are Open To Visual Hacking, Study Finds

Sensitive information contained in documents on a worker’s desk, computer screen or around the office are often at risk of being stolen, according to findings from a global study released Wednesday.