Bounding The Number of Linear Regions in Local Area for Neural Networks with ReLU Activations

no code implementations • 14 Jul 2020 • Rui Zhu, Bo Lin, Haixu Tang

In this paper, we present the first method to estimate the upper bound of the number of linear regions in any sphere in the input space of a given ReLU neural network.

Towards Fair Cross-Domain Adaptation via Generative Learning

no code implementations • 4 Mar 2020 • Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang

Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions.

Domain Adaptation General Classification

Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection

1 code implementation • 2 Aug 2019 • Di Tang, Xiao-Feng Wang, Haixu Tang, Kehuan Zhang

A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a specific label.

Cryptography and Security

Understanding Membership Inferences on Well-Generalized Learning Models

1 code implementation • 13 Feb 2018 • Yunhui Long, Vincent Bindschaedler, Lei Wang, Diyue Bu, Xiao-Feng Wang, Haixu Tang, Carl A. Gunter, Kai Chen

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model.

Inference Attack Membership Inference Attack