most citedNonlinear Transformations Against Unlearnable Datasets

2 citations · 2 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG20262 cited

Nonlinear Transformations Against Unlearnable Datasets

Thushari Hapuarachchi, Jing Lin, Kaiqi Xiong +2

Automated scraping stands out as a common method for collecting data in deep learning models without the authorization of data owners. Recent studies have begun to tackle the priva…

cs.LG2026

SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions

Thushari Hapuarachchi, Kaiqi Xiong

There is recently a serious issue that Deep Neural Networks (DNNs) training uses more and more unauthorized data. A clean-label generalization attack, one type of data poisoning at…

cs.LG2025

Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustness

Long Dang, Thushari Hapuarachchi, Kaiqi Xiong +1

Adversarial training is an effective method to improve the machine learning (ML) model robustness. Most existing studies typically consider the Rectified linear unit (ReLU) activat…

cs.CV2025

Securing Traffic Sign Recognition Systems in Autonomous Vehicles

Thushari Hapuarachchi, Long Dang, Kaiqi Xiong

Deep Neural Networks (DNNs) are widely used for traffic sign recognition because they can automatically extract high-level features from images. These DNNs are trained on large-sca…

cs.LG2025

SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networks

Long Dang, Thushari Hapuarachchi, Kaiqi Xiong +1

As the development of autonomous and connected vehicles advances, the complexity of modern vehicles increases, with numerous Electronic Control Units (ECUs) integrated into the sys…