← Search

Shitong Zhu

2 accepted papers

2021

Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

NeurIPS 2021poster

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses significant additional challenges in gradient estimation. Query-efficient black…

2020

Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency

ECCV 2020poster

There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs); most of these attacks target object classifiers. Inspired by the observation that humans are able to recognize objects that appear out of place in a scene or along with other unlikely obje…

Cited by 52SourcePDFScholar