Artificial Intelligence (AI)‐based systems are widely employed nowadays to make decisions
that have far‐reaching impact on individuals and society. Their decisions might affect …

Supervised learning techniques construct predictive models by learning from a large
number of training examples, where each training example has a label indicating its ground …

Data collection is a major bottleneck in machine learning and an active research topic in
multiple communities. There are largely two reasons data collection has recently become a …

In a backdoor attack, an adversary injects corrupted data into a model's training dataset in
order to gain control over its predictions on images with a specific attacker-defined trigger. A …

In recent years, the reliability of information on the Internet has emerged as a crucial issue of
modern society. Social network sites (SNSs) have revolutionized the way in which …

Large labeled training sets are the critical building blocks of supervised learning methods
and are key enablers of deep learning techniques. For some applications, creating labeled …

Crowdsourcing has emerged as a novel problem-solving paradigm, which facilitates
addressing problems that are hard for computers, eg, entity resolution and sentiment …

We study the problem of learning conditional generators from noisy labeled samples, where
the labels are corrupted by random noise. A standard training of conditional GANs will not …

With wide deployment of machine learning (ML)-based systems for a variety of applications
including medical, military, automotive, genomic, multimedia, and social networking, there is …

Crowdsourcing enables one to leverage on the intelligence and wisdom of potentially large
groups of individuals toward solving problems. Common problems approached with …