Search Results for author:
Found 3 papers, 2 papers with code
Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification
Furthermore, we conduct a comprehensive evaluation of different loss functions within consistent training frameworks, including noise-based and generator-based.
Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature
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.
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
