‘Deceptive Delight’ Jailbreak Tricks Gen-AI by Embedding Unsafe Topics in Benign Narratives

Deceptive Delight is a new AI jailbreak that has been successfully tested against eight models with an average success rate of 65%.

The post ‘Deceptive Delight’ Jailbreak Tricks Gen-AI by Embedding Unsafe Topics in Benign Narratives appeared first on SecurityWeek.

This article has been indexed from SecurityWeek

Read the original article: