Researchers jailbreak AI models Meta, Gemini to generate phishing emails; 11% of 108 elderly California participants clicked malicious links in end-to-end study with Reuters, prompting Senate hearing request.

Can AI Models be Jailbroken to Phish Elderly Victims? An End-to-End Evaluation

TLDR: We worked with Reuters on an article and just released a paper on the impacts of AI scams on elderly people.Fred Heiding and I have been working for multiple years on studying how AI systems can be used for fraud or scams online. A few months ago, we got into contact with Steve Stecklow, a journalist at Reuters. We wanted to do a report on how scammers use AI to target people with a focus on elderly people. There have been many individual stories about how elderly people were frequently th...