no code implementations • 20 Jun 2023 • Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li
Furthermore, we conduct a comprehensive evaluation of different loss functions within consistent training frameworks, including noise-based and generator-based.
1 code implementation • 2 May 2023 • Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li, Zhun Zhong
Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models.
2 code implementations • 7 Mar 2023 • Juanjuan Weng, Zhiming Luo, Zhun Zhong, Shaozi Li, Nicu Sebe
In this work, we provide a comprehensive investigation of the CE loss function and find that the logit margin between the targeted and untargeted classes will quickly obtain saturation in CE, which largely limits the transferability.