Deep-Evasion: Turn Deep Neural Network into Evasive Self-Contained Cyber-Physical Malware

Deep Neural Network (DNN) based intelligent Cyber-Physical Systems (CPS) are becoming more and more popular across all aspects of our lives. Unfortunately, such a promising trend implies a dangerous feature that allows code to be mixed with data in DNN models and triggered by a targeted physical object without harming the DNN inference accuracy. In this work, we investigate such an emerging attack, namely "Deep-Evasion", turning DNN into evasive self-contained malware on CPS. We prototype "Deep-Evasion" on Nvidia Jetson TX2 embedded device and demonstrate a Denial-of-Service (DoS) attack as our proof of concept. Experimental results show "Deep-Evasion" is feasible, reliable and scalable on CPS.