Researchers Manipulate o1, o3, Gemini 2.0 Flash Thinking and DeepSeek-R1. The new generation of reasoning artificial intelligence chatbots is susceptible to a jailbreaking method that hijacks models’ safety pathways, reducing their ability to detect harmful content. The attack modifies the reasoning processes and reintegrates the changes into the original queries.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/ai-hijacked-new-jailbreak-exploits-chain-of-thought-a-27594
