Search Results for author:
Found 13 papers, 3 papers with code
Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models
Prioritizing fairness is of central importance in artificial intelligence (AI) systems, especially for those societal applications, e. g., hiring systems should recommend applicants equally from different demographic groups, and risk assessment systems must eliminate racism in criminal justice.
Optimized Separable Convolution: Yet Another Efficient Convolution Operator
In this research, we propose a novel and principled operator called optimized separable convolution by optimal design for the internal number of groups and kernel sizes for general separable convolutions can achieve the complexity of O(C^{\frac{3}{2}}K).
A High-Performance, Reconfigurable, Fully Integrated Time-Domain Reflectometry Architecture Using Digital I/Os
These results demonstrate that a fully reconfigurable and highly integrated TDR (iTDR) can be implemented on a field-programmable gate array (FPGA) chip without using any external circuit components.
Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations
The current state-of-the-art approaches for medical image classification rely on using the de-facto method for ConvNets - fine-tuning.
Rethinking Convolution: Towards an Optimal Efficiency
In this research, we propose a novel operator called \emph{optimal separable convolution} which can be calculated at $O(C^{\frac{3}{2}}KHW)$ by optimal design for the internal number of groups and kernel sizes for general separable convolutions.
Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object Tracking
Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models.
Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
Finally, we conduct extensive experiments using a wide range of datasets and the experiment results show that our AT+ALP achieves the state of the art defense performance.
Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield
Many recent works demonstrated that Deep Learning models are vulnerable to adversarial examples. Fortunately, generating adversarial examples usually requires white-box access to the victim model, and the attacker can only access the APIs opened by cloud platforms.
Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking
Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models.
Enhancing Cross-task Transferability of Adversarial Examples with Dispersion Reduction
Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i. e., they maintain their effectiveness even against other models.
Network Iterative Learning for Dynamic Deep Neural Networks via Morphism
In this research, we present a novel learning scheme called network iterative learning for deep neural networks.
Modularized Morphing of Neural Networks
Different from existing work where basic morphing types on the layer level were addressed, we target at the central problem of network morphism at a higher level, i. e., how a convolutional layer can be morphed into an arbitrary module of a neural network.
Network Morphism
The second requirement for this network morphism is its ability to deal with non-linearity in a network.
