Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Ding, A. Adam"'
Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained encoder--ha
Externí odkaz:
http://arxiv.org/abs/2411.12508
Pretrained Deep Neural Networks (DNNs), developed from extensive datasets to integrate multifaceted knowledge, are increasingly recognized as valuable intellectual property (IP). To safeguard these models against IP infringement, strategies for owner
Externí odkaz:
http://arxiv.org/abs/2410.08015
Graph-structured data is integral to many applications, prompting the development of various graph representation methods. Graph autoencoders (GAEs), in particular, reconstruct graph structures from node embeddings. Current GAE models primarily utili
Externí odkaz:
http://arxiv.org/abs/2410.03396
Autor:
Jafari, Arezoo, Drummond, Priscila De Azevedo, Nishigaya, Dominic, Bhimani, Shawn, Ding, Aidong Adam, Farrell, Amy, Maass, Kayse Lee
Agricultural workers are essential to the supply chain for our daily food and yet, many face harmful work conditions, including garnished wages, and other labor violations. Workers on H-2A visas are particularly vulnerable due to the precarity of the
Externí odkaz:
http://arxiv.org/abs/2306.04003
Biomarker is a critically important tool in modern clinical diagnosis, prognosis, and classification/prediction. However, there are fiscal and analytical barriers to biomarker research. Selective Genotyping is an approach to increasing study power an
Externí odkaz:
http://arxiv.org/abs/2208.00353
Modern deep neural networks (DNNs) are vulnerable to adversarial attacks and adversarial training has been shown to be a promising method for improving the adversarial robustness of DNNs. Pruning methods have been considered in adversarial context to
Externí odkaz:
http://arxiv.org/abs/2202.06488
The rapid development in Internet of Medical Things (IoMT) boosts the opportunity for real-time health monitoring using various data types such as electroencephalography (EEG) and electrocardiography (ECG). Security issues have significantly impeded
Externí odkaz:
http://arxiv.org/abs/2202.03652
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed data across
Externí odkaz:
http://arxiv.org/abs/2202.02448
Differential privacy schemes have been widely adopted in recent years to address issues of data privacy protection. We propose a new Gaussian scheme combining with another data protection technique, called random orthogonal matrix masking, to achieve
Externí odkaz:
http://arxiv.org/abs/2201.04211
Autor:
Shi, Xupeng, Ding, A. Adam
State-of-art deep neural networks (DNN) are vulnerable to attacks by adversarial examples: a carefully designed small perturbation to the input, that is imperceptible to human, can mislead DNN. To understand the root cause of adversarial examples, we
Externí odkaz:
http://arxiv.org/abs/1910.12163