Generating watermarked adversarial texts
Adversarial example generation (AEG) has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to improve the robustness of DNN models. Due to t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SPIE
2023
|
| Subjects: | |
| Online Access: | View Fulltext in Publisher View in Scopus |