White Rose Consortium ePrints Repository

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, background): “Typical defenses against data poisoning attacks involve Data Sanitization [46] which uses outlier detection [47], however Koh et al.”
Stronger data poisoning attacks break data sanitization defenses (2018, background): “A common and often effective defense against data poisoning attacks is data sanitization, which use anomaly detectors to filter out training points that look suspicious (Hodge & Austin, 2004; Cretu et al., 2008; Paudice et al., 2018).”
Sever: A Robust Meta-Algorithm for Stochastic Optimization (2018, methodology): “Popular methods include RANSAC [FB81], minimum covariance determinant [RD99], removal based on k-nearest neighbors [BKNS00], and Huberizing the loss [Owe07] (see [HA04] for a comprehensive survey).”
Learning Placeholders for Open-Set Recognition (2021, background): “The problem of out-ofdistribution detection [10, 17, 1], anomaly detection [4, 18, 25] and novelty detection [11, 32, 41, 21, 43] are related topics to open-set recognition.”
Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection (2019, methodology): “[13] summarizes several effective outlier detection methods, including k-nearest neighbors (knn) [14], k-means [23] and principal components analysis 1(0.”
Deep Learning for Anomaly Detection (2020, background): “urrent deep anomaly detection methods and their capabilities in addressing these challenges, and finally presents a number of future opportunities in this area. As a popular area, a number of studies [2, 4, 16, 28, 54, 63, 178] have been dedicated to the categorization and review of anomaly detectio”
Data collection and quality challenges in deep learning: a data-centric AI perspective (2021, methodology): “Data sanitization techniques [52,79,119] have been proposed throughout”
Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids (2018, methodology): “The typical approaches used in anomaly detection in smart grids mainly include SVM, clustering, and classification [27].”
Learning with Augmented Class by Exploiting Unlabeled Data (2014, background): “The outlier detection problem (Hodge and Austin 2004) requires to identify abnormal instances from a given data set.”