In standard adversarial training, models are optimized to fit one-hot la...
With the power of large pretrained language models, various research wor...
Randomized smoothing is currently the state-of-the-art method that provi...
Fair Active Learning (FAL) utilized active learning techniques to achiev...
Malicious attackers can generate targeted adversarial examples by imposi...
Much literature has shown that prompt-based learning is an efficient met...
Deep learning models are being integrated into a wide range of high-impa...
Adversarial machine learning research has recently demonstrated the
feas...
Given the ability to directly manipulate image pixels in the digital inp...
The rapidly growing body of research in adversarial machine learning has...
Deep neural networks (DNNs) have achieved great success in solving a var...
We consider the problem of learning from distributed data in the agnosti...
We study the task of online boosting--combining online weak learners int...