research
∙
08/04/2023
Improving Scene Graph Generation with Superpixel-Based Interaction Learning
Recent advances in Scene Graph Generation (SGG) typically model the rela...
share
research
∙
06/24/2023
HODOR: Shrinking Attack Surface on Node.js via System Call Limitation
Node.js provides Node.js applications with system interaction capabiliti...
research
∙
05/15/2023
Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs
Dynamic scene graphs generated from video clips could help enhance the s...
research
∙
04/14/2023
FairRec: Fairness Testing for Deep Recommender Systems
Deep learning-based recommender systems (DRSs) are increasingly and wide...
research
∙
12/29/2022
Towards Comprehensively Understanding the Run-time Security of Programmable Logic Controllers: A 3-year Empirical Study
Programmable Logic Controllers (PLCs) are the core control devices in In...
research
∙
12/23/2022
Two-Sample Test for High-Dimensional Covariance Matrices: a normal-reference approach
Testing the equality of the covariance matrices of two high-dimensional ...
research
∙
08/24/2022
TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination
Discrimination has been shown in many machine learning applications, whi...
research
∙
08/04/2022
Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers
Keyword spotting (KWS) is beneficial for voice-based user interactions w...
research
∙
05/25/2022
VeriFi: Towards Verifiable Federated Unlearning
Federated learning (FL) is a collaborative learning paradigm where parti...
research
∙
03/31/2022
A simplified nonsmooth nonconvex bundle method with applications to security-constrained ACOPF problems
An optimization algorithm for a group of nonsmooth nonconvex problems in...
research
∙
02/08/2022
K-ST: A Formal Executable Semantics of PLC Structured Text Language
Programmable Logic Controllers (PLCs) are responsible for automating pro...
research
∙
12/29/2021
Repairing Adversarial Texts through Perturbation
It is known that neural networks are subject to attacks through adversar...
research
∙
12/25/2021
NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification
Deep neural networks (DNNs) have demonstrated their outperformance in va...
research
∙
12/14/2021
Better Pay Attention Whilst Fuzzing
Fuzzing is one of the prevailing methods for vulnerability detection. Ho...
research
∙
12/10/2021
Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
Deep learning (DL) models, especially those large-scale and high-perform...
research
∙
11/17/2021
Fairness Testing of Deep Image Classification with Adequacy Metrics
As deep image classification applications, e.g., face recognition, becom...
research
∙
07/17/2021
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
Although deep learning has demonstrated astonishing performance in many ...
research
∙
05/22/2021
Adversarial Attacks and Mitigation for Anomaly Detectors of Cyber-Physical Systems
The threats faced by cyber-physical systems (CPSs) in critical infrastru...
research
∙
03/13/2021
Attack as Defense: Characterizing Adversarial Examples using Robustness
As a new programming paradigm, deep learning has expanded its applicatio...
research
∙
02/19/2021
A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification
Graph convolutional neural network provides good solutions for node clas...
research
∙
02/11/2021
RobOT: Robustness-Oriented Testing for Deep Learning Systems
Recently, there has been a significant growth of interest in applying so...
research
∙
12/03/2020
Towards Repairing Neural Networks Correctly
Neural networks are increasingly applied to support decision making in s...
research
∙
10/15/2020
Improving Neural Network Verification through Spurious Region Guided Refinement
We propose a spurious region guided refinement approach for robustness v...
research
∙
08/11/2020
Towards Plausible Differentially Private ADMM Based Distributed Machine Learning
The Alternating Direction Method of Multipliers (ADMM) and its distribut...
research
∙
11/14/2019
There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
Deep neural networks (DNN) are increasingly applied in safety-critical s...
research
∙
09/22/2019
Analyzing Recurrent Neural Network by Probabilistic Abstraction
Neural network is becoming the dominant approach for solving many real-w...
research
∙
12/14/2018
Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing
Deep neural networks (DNN) have been shown to be useful in a wide range ...
research
∙
05/14/2018
Detecting Adversarial Samples for Deep Neural Networks through Mutation Testing
Recently, it has been shown that deep neural networks (DNN) are subject ...
research
∙
12/12/2017