Attackers Can Manipulate AI Memory to Spread Lies
Tested on Three OpenAI Models, 'Minja' Has High Injection and Attack Rates
A memory injection attack dubbed Minja turns AI chatbots into unwitting agents of misinformation, requiring no hacking and just a little clever prompting. The exploit allows attackers to poison an AI model's memory with deceptive information, potentially altering its responses for all users.
A memory injection attack dubbed Minja turns AI chatbots into unwitting agents of misinformation, requiring no hacking and just a little clever prompting. The exploit allows attackers to poison an AI model's memory with deceptive information, potentially altering its responses for all users.