Even Artificial Neural Networks Can Have Exploitable ‘Backdoors’
Even Artificial Neural Networks Can Have Exploitable ‘Backdoors’
Early in August, NYU professor Siddharth Garg checked for traffic, and then put a yellow Post-it onto a stop sign outside the Brooklyn building in which he works. When he and two colleagues showed a photo of the scene to their road-sign detector software, it was 95 percent sure the stop sign in fact displayed a speed limit. The stunt demonstrated a potential security headache for engineers…