OpenAI, Google pushing new AI models easily tricked into making nudes, researchers say

Researchers have identified a vulnerability in AI models developed by OpenAI and Google that can be easily tricked into generating explicit images, highlighting potential flaws in safeguards against AI-generated nude content. The attack method, which has not been publicly disclosed, exploits weaknesses in the models' safety measures, allowing attackers to manipulate the AI into creating explicit images. This raises concerns about the effectiveness of current safeguards and the potential for misuse of AI-generated content. The researchers have not provided further details on the attack method, citing the need to avoid encouraging malicious activity.