Black box video confrontation sample generation method and evaluation method based on reinforcement learning

• Main Authors: LIANG KAI, LIU RONGKAI, HU CHAO, SHI HEYUAN, ZHAN YU, YU RUISHI
• Format: Patent
• Language: Chinese; English
• Published: 08.11.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention discloses a black box video adversarial sample generation method based on reinforcement learning. The method comprises the following steps: acquiring original video data and segmenting the original video data to obtain a video block set; inserting position information into the video block set to obtain the video block set with the position information; performing visual feature extraction to obtain features of the video blocks; extracting the video block set with the position information to obtain a key video block set; iterating the key video block set to obtain an estimation gradient; generating a confrontation sample value and constructing a corresponding loss function; and inputting the confrontation sample value into the target video model to obtain a return value, and obtaining a finally constructed confrontation sample according to the return value and the loss function value. The invention further discloses an evaluation method comprising the black box video confrontation sample generati