{"id":56223,"date":"2024-06-03T13:02:38","date_gmt":"2024-06-03T13:02:38","guid":{"rendered":"https:\/\/packetstormsecurity.com\/news\/view\/35954\/Baidu-Robo-Cars-Crashed-With-Tinfoil-And-Paint-Daubed-On-Cardboard.html"},"modified":"2024-06-03T13:02:38","modified_gmt":"2024-06-03T13:02:38","slug":"baidu-robo-cars-crashed-with-tinfoil-and-paint-daubed-on-cardboard","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/baidu-robo-cars-crashed-with-tinfoil-and-paint-daubed-on-cardboard\/","title":{"rendered":"Baidu Robo-Cars Crashed With Tinfoil And Paint Daubed On Cardboard"},"content":{"rendered":"

A team of researchers from prominent universities \u2013 including SUNY Buffalo, Iowa State, UNC Charlotte, and Purdue \u2013 were able to turn an autonomous vehicle (AV) operated on the open sourced Apollo driving platform from Chinese web giant Baidu into a deadly weapon by tricking its multi-sensor fusion system.<\/p>\n

“Extensive experiments based on a real-world AV testbed show that the proposed attack can continuously hide a target vehicle from the perception system of a victim AV using only two small adversarial objects,” explained<\/a> the researchers, whose work was published last week in The 30th Annual International Conference on Mobile Computing and Networking.<\/p>\n

While others<\/a> have proven vulnerabilities inherent in AV systems, this particular team expanded on single-sensing modality or camera-LiDAR manipulation, and tricked systems that employ Lidar, camera, and radar together.<\/p>\n