activity
20192022
most citedTowards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack

58 citations · 61 across the 6 of their papers we have counts for

collaborators

5 papers

eess.IV20223 cited

Low-Dose CT Denoising via Sinogram Inner-Structure Transformer

Liutao Yang, Zhongnian Li, Rongjun Ge +3

Low-Dose Computed Tomography (LDCT) technique, which reduces the radiation harm to human bodies, is now attracting increasing interest in the medical imaging field. As the image qu…

cs.CV2022

Scale-Invariant Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

Mengting Xu, Tao Zhang, Zhongnian Li +1

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrate…

cs.CV202158 cited

Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack

Mengting Xu, Tao Zhang, Zhongnian Li +2

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown d…

cs.LG2021

Improving the Certified Robustness of Neural Networks via Consistency Regularization

Mengting Xu, Tao Zhang, Zhongnian Li +1

A range of defense methods have been proposed to improve the robustness of neural networks on adversarial examples, among which provable defense methods have been demonstrated to b…

cs.CV2019

SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction

Zhongnian Li, Tao Zhang, Peng Wan +1

Generative Adversarial Networks (GANs) are powerful tools for reconstructing Compressed Sensing Magnetic Resonance Imaging (CS-MRI). However most recent works lack exploration of s…