← Search

Shenglin Zhao

2 accepted papers

2020

Boosting the Transferability of Adversarial Samples via Attention

CVPR 2020poster

The widespread deployment of deep models necessitates the assessment of model vulnerability in practice, especially for safety- and security-sensitive domains such as autonomous driving and medical diagnosis. Transfer-based attacks against image classifiers thus elicit mounting interest, where attac…

Cited by 182PDFcodeScholar
2020

Towards Global Explanations of Convolutional Neural Networks With Concept Attribution

CVPR 2020oral

With the growing prevalence of convolutional neural networks (CNNs), there is an urgent demand to explain their behaviors. Global explanations contribute to understanding model predictions on a whole category of samples, and thus have attracted increasing interest recently. However, existing methods…

Cited by 68PDFScholar