
-
Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
Prior works on formalizing explanations of a graph neural network (GNN) ...
read it
-
Generating Adversarial Computer Programs using Optimized Obfuscations
Machine learning (ML) models that learn and predict properties of comput...
read it
-
On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
Although deep learning (DL) has received much attention in accelerated M...
read it
-
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Model-agnostic meta-learning (MAML) has emerged as one of the most succe...
read it
-
Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
In deep model compression, the recent finding "Lottery Ticket Hypothesis...
read it
-
Fast Training of Provably Robust Neural Networks by SingleProp
Recent works have developed several methods of defending neural networks...
read it
-
Self-Progressing Robust Training
Enhancing model robustness under new and even adversarial environments i...
read it
-
Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
In this work, we focus on the study of stochastic zeroth-order (ZO) opti...
read it
-
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
The computer vision world has been re-gaining enthusiasm in various pre-...
read it
-
Training Stronger Baselines for Learning to Optimize
Learning to optimize (L2O) has gained increasing attention since classic...
read it
-
Higher-Order Certification for Randomized Smoothing
Randomized smoothing is a recently proposed defense against adversarial ...
read it
-
TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
Multivariate time series (MTS) data are becoming increasingly ubiquitous...
read it
-
Learned Fine-Tuner for Incongruous Few-Shot Learning
Model-agnostic meta-learning (MAML) effectively meta-learns an initializ...
read it
-
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
When the training data are maliciously tampered, the predictions of the ...
read it
-
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
In natural language processing (NLP), enormous pre-trained models like B...
read it
-
Proper Network Interpretability Helps Adversarial Robustness in Classification
Recent works have empirically shown that there exist adversarial example...
read it
-
Can 3D Adversarial Logos Cloak Humans?
With the trend of adversarial attacks, researchers attempt to fool train...
read it
-
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case
Although graph neural networks (GNNs) have made great progress recently ...
read it
-
Solving Constrained CASH Problems with ADMM
The CASH problem has been widely studied in the context of automated con...
read it
-
Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning
Pretrained models from self-supervision are prevalently used in fine-tun...
read it
-
Rethinking Randomized Smoothing for Adversarial Robustness
The fragility of modern machine learning models has drawn a considerable...
read it
-
Defending against Backdoor Attack on Deep Neural Networks
Although deep neural networks (DNNs) have achieved a great success in va...
read it
-
Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
Graph Neural Networks (GNNs) have made significant advances on several f...
read it
-
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency
Structured weight pruning is a representative model compression techniqu...
read it
-
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
Weight pruning has been widely acknowledged as a straightforward and eff...
read it
-
Towards Verifying Robustness of Neural Networks Against Semantic Perturbations
Verifying robustness of neural networks given a specified threat model i...
read it
-
Development of Clinical Concept Extraction Applications: A Methodology Review
Our study provided a review of the development of clinical concept extra...
read it
-
A Review of the End-to-End Methodologies for Clinical Concept Extraction
Our study provided a review of the concept extraction literature from Ja...
read it
-
How can AI Automate End-to-End Data Science?
Data science is labor-intensive and human experts are scarce but heavily...
read it
-
Evading Real-Time Person Detectors by Adversarial T-shirt
It is known that deep neural networks (DNNs) could be vulnerable to adve...
read it
-
An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy
Our goal is to understand the so-called trade-off between fairness and a...
read it
-
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
The adaptive momentum method (AdaMM), which uses past gradients to updat...
read it
-
Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
In this paper, we study the problem of constrained robust (min-max) opti...
read it
-
Reweighted Proximal Pruning for Large-Scale Language Representation
Recently, pre-trained language representation flourishes as the mainstay...
read it
-
Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
We study the most practical problem setup for evaluating adversarial rob...
read it
-
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics wh...
read it
-
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Graph neural networks (GNNs) which apply the deep neural networks to gra...
read it
-
Beyond Adversarial Training: Min-Max Optimization in Adversarial Attack and Defense
The worst-case training principle that minimizes the maximal adversarial...
read it
-
Automated Machine Learning via ADMM
We study the automated machine learning (AutoML) problem of jointly sele...
read it
-
Interpreting Adversarial Examples by Activation Promotion and Suppression
It is widely known that convolutional neural networks (CNNs) are vulnera...
read it
-
Second Rethinking of Network Pruning in the Adversarial Setting
It is well known that deep neural networks (DNNs) are vulnerable to adve...
read it
-
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM
Weight pruning and weight quantization are two important categories of D...
read it
-
CREATE: Cohort Retrieval Enhanced by Analysis of Text from Electronic Health Records using OMOP Common Data Model
Background: Widespread adoption of electronic health records (EHRs) has ...
read it
-
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Verifying robustness of neural network classifiers has attracted great i...
read it
-
A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
Many model compression techniques of Deep Neural Networks (DNNs) have be...
read it
-
Progressive Weight Pruning of Deep Neural Networks using ADMM
Deep neural networks (DNNs) although achieving human-level performance i...
read it
-
Is Ordered Weighted ℓ_1 Regularized Regression Robust to Adversarial Perturbation? A Case Study on OSCAR
Many state-of-the-art machine learning models such as deep neural networ...
read it
-
On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization
This paper studies a class of adaptive gradient based momentum algorithm...
read it
-
Structured Adversarial Attack: Towards General Implementation and Better Interpretability
When generating adversarial examples to attack deep neural networks (DNN...
read it
-
Latent heterogeneous multilayer community detection
We propose a method for simultaneously detecting shared and unshared com...
read it