AI Networks Are More Vulnerable To Malicious Attacks Than Previously Thought

AI Networks Are More Vulnerable To Malicious Attacks Than Previously Thought

Credit: Steve Johnson Artificial intelligence tools hold promise for applications ranging from autonomous vehicles to the interpretation of medical images. However, a new study finds these AI tools are more vulnerable than previously thought to targeted attacks that effectively force AI systems to make bad decisions. At issue are so-called “adversarial attacks,” in which someone manipulates the data being fed into an AI system in order to confus…