The Limitations of Deep Learning Methods in Realistic Adversarial Settings

Generating Adversarial Texts by the Universal Tail Word Addition Attack

Y **e, Z Gu, R Tan, C Luo, X Song, H Wang - Asia-Pacific Web (APWeb) …, 2024 - Springer
Deep neural networks (DNNs) are vulnerable to adversarial examples, which can mislead
models without affecting normal judgment of humans. In the image field, such adversarial …
保存 引用 関連記事 全 2 バージョン