1.8k citations · 9.5k across the 166 of their papers we have counts for
28 papers · 1 filter
Overcoming Catastrophic Forgetting by Generative Regularization
Patrick H. Chen, Wei Wei, Cho-jui Hsieh +1
In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general f…
GraphDefense: Towards Robust Graph Convolutional Networks
Xiaoyun Wang, Xuanqing Liu, Cho-Jui Hsieh
In this paper, we study the robustness of graph convolutional networks (GCNs). Despite the good performance of GCNs on graph semi-supervised learning tasks, previous works have sho…
Enhancing Certifiable Robustness via a Deep Model Ensemble
Huan Zhang, Minhao Cheng, Cho-Jui Hsieh
We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically imp…
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
Xuanqing Liu, Si Si, Xiaojin Zhu +2
In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals,…
BOSH: An Efficient Meta Algorithm for Decision-based Attacks
Zhenxin Xiao, Puyudi Yang, Yuchen Jiang +2
Adversarial example generation becomes a viable method for evaluating the robustness of a machine learning model. In this paper, we consider hard-label black-box attacks (a.k.a. de…
Learning to Learn by Zeroth-Order Oracle
Yangjun Ruan, Yuanhao Xiong, Sashank Reddi +2
In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In thi…
Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
Utkarsh Ojha, Krishna Kumar Singh, Cho-Jui Hsieh +1
We propose a novel unsupervised generative model that learns to disentangle object identity from other low-level aspects in class-imbalanced data. We first investigate the issues s…
Natural Adversarial Sentence Generation with Gradient-based Perturbation
Yu-Lun Hsieh, Minhao Cheng, Da-Cheng Juan +3
This work proposes a novel algorithm to generate natural language adversarial input for text classification models, in order to investigate the robustness of these models. It invol…
Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
Minhao Cheng, Simranjit Singh, Patrick Chen +3
We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for genera…
Temporal Collaborative Ranking Via Personalized Transformer
Liwei Wu, Shuqing Li, Cho-Jui Hsieh +1
The collaborative ranking problem has been an important open research question as most recommendation problems can be naturally formulated as ranking problems. While much of collab…
VisualBERT: A Simple and Performant Baseline for Vision and Language
Liunian Harold Li, Mark Yatskar, Da Yin +2
We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly…
Evaluating the Robustness of Nearest Neighbor Classifiers: A Primal-Dual Perspective
Lu Wang, Xuanqing Liu, Jinfeng Yi +2
We study the problem of computing the minimum adversarial perturbation of the Nearest Neighbor (NN) classifiers. Previous attempts either conduct attacks on continuous approximatio…
ML-LOO: Detecting Adversarial Examples with Feature Attribution
Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh +2
Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation…
Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
Xuanqing Liu, Tesi Xiao, Si Si +3
Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discr…
Efficient Neural Interaction Function Search for Collaborative Filtering
Quanming Yao, Xiangning Chen, James Kwok +2
In collaborative filtering (CF), interaction function (IFC) plays the important role of capturing interactions among items and users. The most popular IFC is the inner product, whi…
Convergence of Adversarial Training in Overparametrized Neural Networks
Ruiqi Gao, Tianle Cai, Haochuan Li +3
Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial tr…
Towards Stable and Efficient Training of Verifiably Robust Neural Networks
Huan Zhang, Hongge Chen, Chaowei Xiao +5
Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under pertur…
Robustness Verification of Tree-based Models
Hongge Chen, Huan Zhang, Si Si +3
We study the robustness verification problem for tree-based models, including decision trees, random forests (RFs) and gradient boosted decision trees (GBDTs). Formal robustness ve…
Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
Liwei Wu, Hsiang-Fu Yu, Nikhil Rao +2
In this paper, we consider recommender systems with side information in the form of graphs. Existing collaborative filtering algorithms mainly utilize only immediate neighborhood i…
Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
Liwei Wu, Shuqing Li, Cho-Jui Hsieh +1
In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters. Tikhonov regularization, graph-based regularization, and hard param…
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
Wei-Lin Chiang, Xuanqing Liu, Si Si +3
Graph convolutional network (GCN) has been successfully applied to many graph-based applications; however, training a large-scale GCN remains challenging. Current SGD-based algorit…
Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attacks
Jun-Ho Choi, Huan Zhang, Jun-Hyuk Kim +2
Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many computer vision applications. Thi…
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Yang You, Jing Li, Sashank Reddi +7
Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization me…
Efficient Contextual Representation Learning Without Softmax Layer
Liunian Harold Li, Patrick H. Chen, Cho-Jui Hsieh +1
Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the l…