How to properly set the privacy parameter in differential privacy (DP) h...
Graph Neural Networks have achieved tremendous success in modeling compl...
While numerous defense methods have been proposed to prohibit potential
...
Under missing-not-at-random (MNAR) sample selection bias, the performanc...
Deep learning models have recently become popular for detecting maliciou...
Learning disentangled causal representations is a challenging problem th...
In the problem of online learning for changing environments, data are
se...
The shift between the training and testing distributions is commonly due...
Graph neural networks (GNNs) are susceptible to privacy inference attack...
Anomaly detection in sequential data has been studied for a long time be...
The fairness-aware online learning framework has arisen as a powerful to...
Anomaly detection has a wide range of real-world applications, such as b...
This paper explores previously unknown backdoor risks in HyperNet-based
...
Over the past several years, a slew of different methods to measure the
...
Both fair machine learning and adversarial learning have been extensivel...
Recent research on fair regression focused on developing new fairness no...
In online recommendation, customers arrive in a sequential and stochasti...
The underlying assumption of many machine learning algorithms is that th...
Educational content labeled with proper knowledge components (KCs) are
p...
Algorithmic fairness is becoming increasingly important in data mining a...
Detecting anomalous events in online computer systems is crucial to prot...
Personalized recommendation based on multi-arm bandit (MAB) algorithms h...
Federated learning is an emerging framework that builds centralized mach...
Insider threats, as one type of the most challenging threats in cyberspa...
When we enforce differential privacy in machine learning, the utility-pr...
The darknet markets are notorious black markets in cyberspace, which inv...
Preserving differential privacy has been well studied under centralized
...
Fair machine learning is receiving an increasing attention in machine
le...
A recent trend of fair machine learning is to define fairness as
causali...
Insiders usually cause significant losses to organizations and are hard ...
In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM)...
Fairness-aware classification is receiving increasing attention in the
m...
Many online platforms have deployed anti-fraud systems to detect and pre...
Fairness-aware learning is increasingly important in data mining.
Discri...
Predictive models learned from historical data are widely used to help
c...
Many online applications, such as online social networks or knowledge ba...
In this paper, we focus on developing a novel mechanism to preserve
diff...
The remarkable development of deep learning in medicine and healthcare d...
Wikipedia is the largest online encyclopedia that allows anyone to edit
...
Task-specific word identification aims to choose the task-related words ...
Discrimination-aware classification is receiving an increasing attention...