114 citations · 1k across the 73 of their papers we have counts for
15 papers · 1 filter
Towards Verifying Robustness of Neural Networks Against Semantic Perturbations
Jeet Mohapatra, Tsui-Wei, Weng +3
Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the -norm t…
How can AI Automate End-to-End Data Science?
Charu Aggarwal, Djallel Bouneffouf, Horst Samulowitz +9
Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it. This makes data science time consuming and restricted to experts with the r…
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Xiangyi Chen, Sijia Liu, Kaidi Xu +4
The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optim…
Adversarial T-shirt! Evading Person Detectors in A Physical World
Kaidi Xu, Gaoyuan Zhang, Sijia Liu +6
It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching advers…
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Sanghamitra Dutta, Dennis Wei, Hazar Yueksel +3
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should dec…
Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
Sijia Liu, Songtao Lu, Xiangyi Chen +5
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective fun…
Reweighted Proximal Pruning for Large-Scale Language Representation
Fu-Ming Guo, Sijia Liu, Finlay S. Mungall +2
Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can…
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…
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
Pu Zhao, Sijia Liu, Pin-Yu Chen +4
Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average c…
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Kaidi Xu, Hongge Chen, Sijia Liu +4
Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However,…
Adversarial Attack Generation Empowered by Min-Max Optimization
Jingkang Wang, Tianyun Zhang, Sijia Liu +4
The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing ad…
An ADMM Based Framework for AutoML Pipeline Configuration
Sijia Liu, Parikshit Ram, Deepak Vijaykeerthy +6
We study the AutoML problem of automatically configuring machine learning pipelines by jointly selecting algorithms and their appropriate hyper-parameters for all steps in supervis…
Interpreting Adversarial Examples by Activation Promotion and Suppression
Kaidi Xu, Sijia Liu, Gaoyuan Zhang +5
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers. However, i…
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM
Shaokai Ye, Xiaoyu Feng, Tianyun Zhang +11
Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed…
Adversarial Robustness vs Model Compression, or Both?
Shaokai Ye, Kaidi Xu, Sijia Liu +6
It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust…