553 citations · 1.6k across the 70 of their papers we have counts for
14 papers · 1 filter
RobustMQ: Benchmarking Robustness of Quantized Models
Yisong Xiao, Aishan Liu, Tianyuan Zhang +3
Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities wh…
SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency
Yan Wang, Yuhang Li, Ruihao Gong +8
Extensive studies have shown that deep learning models are vulnerable to adversarial and natural noises, yet little is known about model robustness on noises caused by different sy…
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
Simin Li, Jun Guo, Jingqiao Xiu +8
This study probes the vulnerabilities of cooperative multi-agent reinforcement learning (c-MARL) under adversarial attacks, a critical determinant of c-MARL's worst-case performanc…
Improving Robust Fairness via Balance Adversarial Training
Chunyu Sun, Chenye Xu, Chengyuan Yao +5
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the…
Exploring the Relationship between Architecture and Adversarially Robust Generalization
Aishan Liu, Shiyu Tang, Siyuan Liang +4
Adversarial training has been demonstrated to be one of the most effective remedies for defending adversarial examples, yet it often suffers from the huge robustness generalization…
Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
Xiuying Wei, Yunchen Zhang, Xiangguo Zhang +5
Transformer architecture has become the fundamental element of the widespread natural language processing~(NLP) models. With the trends of large NLP models, the increasing memory a…
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons
Haibo Jin, Ruoxi Chen, Haibin Zheng +4
Despite impressive capabilities and outstanding performance, deep neural networks (DNNs) have captured increasing public concern about their security problems, due to their frequen…
Stein Variational Inference for Discrete Distributions
Jun Han, Fan Ding, Xianglong Liu +3
Gradient-based approximate inference methods, such as Stein variational gradient descent (SVGD), provide simple and general-purpose inference engines for differentiable continuous…
Towards Unified INT8 Training for Convolutional Neural Network
Feng Zhu, Ruihao Gong, Fengwei Yu +5
Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can furth…
Training Robust Deep Neural Networks via Adversarial Noise Propagation
Aishan Liu, Xianglong Liu, Chongzhi Zhang +3
In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have…
PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks
Hang Yu, Aishan Liu, Xianglong Liu +5
Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustn…
Fast Subspace Clustering Based on the Kronecker Product
Lei Zhou, Xiao Bai, Xianglong Liu +2
Subspace clustering is a useful technique for many computer vision applications in which the intrinsic dimension of high-dimensional data is often smaller than the ambient dimensio…
Projection Based Weight Normalization for Deep Neural Networks
Lei Huang, Xianglong Liu, Bo Lang +1
Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear netwo…
Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
Lei Huang, Xianglong Liu, Bo Lang +3
Orthogonal matrix has shown advantages in training Recurrent Neural Networks (RNNs), but such matrix is limited to be square for the hidden-to-hidden transformation in RNNs. In thi…