Security researchers have developed an AI worm in a test environment that can automatically spread between generative AI agents – potentially stealing data and sending spam emails. The risk also affects Germany's laboratory medicine and system-relevant healthcare organizations such as DGKL or BDL. Both are addressing AI in healthcare and laboratory medicine at this year's annual congresses. To demonstrate the risks of networked, autonomous AI ecosystems, a group of researchers has created what they believe to be one of the first generative AI worms, which can spread from one system to another and potentially steal data or deploy malware within it. "Basically, it means you now have the ability to carry out a new type of cyberattack that has never existed before," Ben Nassi, a Cornell Tech researcher behind the study, told WIRED. In a research report and a website exclusively with...