Code uploaded to AI developer platform Hugging Face covertly installed backdoors and other types of malware on end user machines, researchers from security firm JFrog said Thursday in a report thats a likely harbinger of whats to come. In all, JFrog researchers said, they found roughly 100 submissions that performed hidden and unwanted actions when they were downloaded and loaded onto an end user device. Most of the flagged machine learning models—all of which went undetected by Hugging Face—

Read the full article at Arstechnica