US 12,462,543 B2
Training method and apparatus of adversarial attack model, generating method and apparatus of adversarial image, electronic device, and storage medium
Jiachen Li, Guangdong (CN); Baoyuan Wu, Guangdong (CN); Yong Zhang, Guangdong (CN); Yanbo Fan, Guangdong (CN); Zhifeng Li, Guangdong (CN); and Wei Liu, Guangdong (CN)
Assigned to Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Guangdong (CN)
Filed on Mar. 9, 2022, as Appl. No. 17/690,797.
Application 17/690,797 is a continuation of application No. PCT/CN2020/128009, filed on Nov. 11, 2020.
Claims priority of application No. 202010107342.9 (CN), filed on Feb. 21, 2020.
Prior Publication US 2022/0198790 A1, Jun. 23, 2022
Int. Cl. G06V 10/778 (2022.01); G06V 10/24 (2022.01); G06V 10/28 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); H04L 9/40 (2022.01)
CPC G06V 10/82 (2022.01) [G06V 10/24 (2022.01); G06V 10/28 (2022.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 2201/07 (2022.01); H04L 63/1433 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A training method of an adversarial attack model including a generator network and a discriminator network, the training method comprising:
using the generator network to generate an adversarial attack image based on a training digital image;
performing, by processing circuitry, an adversarial attack on a target model by applying a geometric transformation to the adversarial attack image and inputting the transformed image to the target model to obtain an adversarial attack result;
obtaining a physical image by printing the training digital image on a physical medium and capturing the physical image of the training digital image printed on the physical medium;
using the discriminator network to perform image discrimination between (i) the adversarial attack image generated from the training digital image and (ii) the physical image captured from a physical representation of the training digital image to determine a discrimination loss; and
training the generator network and the discriminator network to minimize a combined loss function including an adversarial attack loss based on the adversarial attack result and the discrimination loss.