Hyperspectral Image Classification With Adversarial Attack
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2021.3122170
Abstract: The performance of a neural network is highly dependent on the labeled samples. However, the labeled samples are primarily clean, which prevents the network from capturing the features of the samples near the decision boundary.… read more here.
Keywords: adversarial attack; hyperspectral image; classification; boundary adversarial ... See more keywords
Protecting Decision Boundary of Machine Learning Model With Differentially Private Perturbation
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2020.3043382
Abstract: Machine learning service API allows model owners to monetize proprietary models by offering prediction services to third-party users. However, existing literature shows that model parameters are vulnerable to extraction attacks which accumulate prediction queries and… read more here.
Keywords: decision boundary; model; machine learning; perturbation ... See more keywords
Robust and Explainable Fault Diagnosis With Power-Perturbation-Based Decision Boundary Analysis of Deep Learning Models
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Industrial Informatics"
DOI: 10.1109/tii.2022.3207758
Abstract: Robustness of neural network models is important in fault diagnosis (FD) because uncertainty in operating conditions varies the power spectral densities of vibration data; however, it is unknown to users due to the limited explainability… read more here.
Keywords: decision; decision boundary; fault diagnosis; power perturbation ... See more keywords
Decision Boundary Visualization for Counterfactual Reasoning
Sign Up to like & getrecommendations! Published in 2022 at "Computer Graphics Forum"
DOI: 10.1111/cgf.14650
Abstract: Machine learning algorithms are widely applied to create powerful prediction models. With increasingly complex models, humans' ability to understand the decision function (that maps from a high‐dimensional input space) is quickly exceeded. To explain a… read more here.
Keywords: boundary visualization; decision boundary; space; visualization counterfactual ... See more keywords