76 citations · 123 across the 16 of their papers we have counts for
16 papers
Detection and Defense of Unlearnable Examples
Yifan Zhu, Lijia Yu, Xiao-Shan Gao
Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Interne…
Restore Translation Using Equivariant Neural Networks
Yihan Wang, Lijia Yu, Xiao-Shan Gao
Invariance to spatial transformations such as translations and rotations is a desirable property and a basic design principle for classification neural networks. However, the commo…
Isometric 3D Adversarial Examples in the Physical World
Yibo Miao, Yinpeng Dong, Jun Zhu +1
3D deep learning models are shown to be as vulnerable to adversarial examples as 2D models. However, existing attack methods are still far from stealthy and suffer from severe perf…
Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game
Xiao-Shan Gao, Shuang Liu, Lijia Yu
Adversarial deep learning is to train robust DNNs against adversarial attacks, which is one of the major research focuses of deep learning. Game theory has been used to answer some…
Skew-sparse matrix multiplication
Qiao-Long Huang, Ke Ye, Xiao-Shan Gao
Based on the observation that is isomorphic to a quotient skew polynomial ring, we propose a new method for matrix multiplicat…
Adversarial Parameter Attack on Deep Neural Networks
Lijia Yu, Yihan Wang, Xiao-Shan Gao
In this paper, a new parameter perturbation attack on DNNs, called adversarial parameter attack, is proposed, in which small perturbations to the parameters of the DNN are made suc…
Proving Information Inequalities and Identities with Symbolic Computation
Laigang Guo, Raymond W. Yeung, Xiao-Shan Gao
Proving linear inequalities and identities of Shannon's information measures, possibly with linear constraints on the information measures, is an important problem in information t…
Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
Lijia Yu, Xiao-Shan Gao
In this paper, the bias classifier is introduced, that is, the bias part of a DNN with Relu as the activation function is used as a classifier. The work is motivated by the fact th…
A Robust Classification-autoencoder to Defend Outliers and Adversaries
Lijia Yu, Xiao-Shan Gao
In this paper, a robust classification-autoencoder (CAE) is proposed, which has strong ability to recognize outliers and defend adversaries. The main idea is to change the autoenco…
A Generalization of the Concavity of Rényi Entropy Powe
Laigang Guo, Chun-Ming Yuan, Xiao-Shan Gao
Recently, Savaré-Toscani proved that the Rényi entropy power of general probability densities solving the -nonlinear heat equation in is always a concave function…
Analyzing the barren plateau phenomenon in training quantum neural networks with the ZX-calculus
Chen Zhao, Xiao-Shan Gao
In this paper, we propose a general scheme to analyze the gradient vanishing phenomenon, also known as the barren plateau phenomenon, in training quantum neural networks with the Z…
Improve the Robustness and Accuracy of Deep Neural Network with Normalization
Lijia Yu, Xiao-Shan Gao
In this paper, the robustness and accuracy of the deep neural network (DNN) was enhanced by introducing the normalization of the weight matrices of the DNN with Relu…
Lower Bound on Derivatives of Costa's Differential Entropy
Laigang Guo, Chun-Ming Yuan, Xiao-Shan Gao
Several conjectures concern the lower bound for the differential entropy of an -dimensional random vector introduced by Costa. Cheng and Geng conjectured that $H(…
Prove Costa's Entropy Power Inequality and High Order Inequality for Differential Entropy with Semidefinite Programming
Laigang Guo, Chun-Ming Yuan, Xiao-Shan Gao
Costa's entropy power inequality is an important generalization of Shannon's entropy power inequality. Related with Costa's entropy power inequality and a conjecture proposed by Mc…
QDNN: DNN with Quantum Neural Network Layers
Chen Zhao, Xiao-Shan Gao
In this paper, we introduce a quantum extension of classical DNN, QDNN. The QDNN consisting of quantum structured layers can uniformly approximate any continuous function and has m…
Binomial Difference Ideal and Toric Difference Variety
Xiao-Shan Gao, Zhang Huang, Chun-Ming Yuan
In this paper, the concepts of binomial difference ideals and toric difference varieties are defined and their properties are proved. Two canonical representations for Laurent bino…