Image confrontation sample generation device and method based on mobility
A technology for countering samples and generating devices, which is applied to biological neural network models, instruments, character and pattern recognition, etc., can solve the problem of low mobility and achieve the effect of increasing the calculation rate, increasing the success rate, and increasing the attack success rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0039] This experiment is to generate multiple adversarial samples according to the above framework and method, and count the effectiveness of the adversarial samples. The hardware environment and software environment of this experiment are shown in Table 1 below:
[0040] Table 1 Experimental environment configuration
[0041]
[0042] The parameter information used by the adversarial sample generation method is as follows:
[0043] Table 2 Algorithm parameter information
[0044] The maximum number of iterations 1000 PGD iterations 1000 Training autoencoder module parameter p 1 -8
Training autoencoder module parameters λ 0.1 Training autoencoder module parameters β 0.01
[0045] The present invention provides a migration-based image adversarial sample generation device, including the following modules:
[0046] Self-encoder training module: use the image training data set for unsupervised training to obtain an autoencoder;
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More