Companies are putting generative artificial intelligence into their products, like ChatGPT and DALL-E, to lessen how much people need to do and make hard tasks easier.
Instead, worms exploit weaknesses in operating systems, network protocols, or applications to copy themselves and spread from one computer to another autonomously. The new research identifies vulnerable generative AI-powered applications and showcases Morris II’s capability to manipulate them, emphasizing the importance of understanding and mitigating security risks in the evolving AI landscape.Morris II can spread itself through generative AI, tricking the systems, sending spam messages, spreading lies, or taking people’s personal information.
Their research says that the worm could affect two types of generative AI-powered apps. First are the apps that rely on the results produced by the GenAI service to function properly.