• Publications
  • Influence
Boosting Adversarial Attacks with Momentum
TLDR
A broad class of momentum-based iterative algorithms to boost adversarial attacks by integrating the momentum term into the iterative process for attacks, which can stabilize update directions and escape from poor local maxima during the iterations, resulting in more transferable adversarial examples.
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser
TLDR
High-level representation guided denoiser (HGD) is proposed as a defense for image classification by using a loss function defined as the difference between the target model's outputs activated by the clean image and denoised image.
Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network
TLDR
A 3-D deep neural network for automatic diagnosing lung cancer from computed tomography scans that selects the top five nodules based on the detection confidence, evaluates their cancer probabilities, and combines them with a leaky noisy-OR gate to obtain the probability of lung cancer for the subject.
Adversarial Attacks and Defences Competition
TLDR
In this chapter, the structure and organization of the NIPS 2017 competition is described and the solutions developed by several of the top-placing teams are described.
Discovering Adversarial Examples with Momentum
TLDR
A strong attack algorithm named momentum iterative fast gradient sign method (MI-FGSM) is proposed to discover adversarial examples and can serve as a benchmark attack algorithm for evaluating the robustness of various models and defense methods.
Somatostatin Neurons in the Basal Forebrain Promote High-Calorie Food Intake.
TLDR
It is reported that somatostatin neurons and GABAergic neurons in the basal forebrain play specific roles in regulating feeding and suggest that BF SOM neurons play a selective role in hedonic feeding.
Estimation of the Volume of the Left Ventricle From MRI Images Using Deep Neural Networks
TLDR
A system based on neural networks was designed to solve the problem of segmenting human left ventricle in magnetic resonance imaging images and calculating its volume and was ranked the fourth on the test set in this competition.
Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network
TLDR
An artificial intelligence reconstruction system supported by an optimized physiological anatomical-based 3D convolutional neural network that can automatically achieve CTA reconstruction in healthcare services that facilitates clinical workflows and provides an opportunity for clinical technologists to improve humanistic patient care.
A Three-Dimensional Deep Convolutional Neural Network for Automatic Segmentation and Diameter Measurement of Type B Aortic Dissection
TLDR
The performance of efficient segmentation and diameter measurement of TBADs based on the 3D deep CNN was both accurate and stable and is promising for evaluating aortic morphology automatically and alleviating the workload of radiologists in the near future.
...
1
2
...