PUMAD: PU Metric learning for anomaly detection

Ju, Hyunjun; Lee, Dongha; Hwang, Jane; Namkung, Junghyun; Yu, Hwanjo

doi:10.1016/j.ins.2020.03.021

Cited by 32 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DAGMM [81] learns a Gaussian Mixture density model (GMM) over a low-dimensional latent space produced by a deep autoencoder. [24] use metric learning for anomaly detection. Deep Structured Energy-based Model for Anomaly Detection (DSEBM) [77] trains deep energy models such as Convolutional and Recurrent EBMs using denoising score matching instead of maximum likelihood, for performing anomaly detection.…”

Section: Related Workmentioning

confidence: 99%

MStream: Fast Anomaly Detection in Multi-Aspect Streams

Bhatia

Jain

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Given a stream of entries in a multi-aspect data setting i.e., entries having multiple dimensions, how can we detect anomalous activities in an unsupervised manner? For example, in the intrusion detection setting, existing work seeks to detect anomalous events or edges in dynamic graph streams, but this does not allow us to take into account additional attributes of each entry. Our work aims to define a streaming multi-aspect data anomaly detection framework, termed MStream which can detect unusual group anomalies as they occur, in a dynamic manner. MStream has the following properties: (a) it detects anomalies in multi-aspect data including both categorical and numeric attributes; (b) it is online, thus processing each record in constant time and constant memory; (c) it can capture the correlation between multiple aspects of the data. MStream is evaluated over the KDDCUP99, CICIDS-DoS, UNSW-NB 15 and CICIDS-DDoS datasets, and outperforms state-of-the-art baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

MStream: Fast Anomaly Detection in Multi-Aspect Streams

Bhatia

Jain

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

show abstract

“…A relatively new research work proposed in [ 11 ] is a novel method, positive-unlabelled deep metric learning method for anomaly detection (PUMAD), which effectively identifies various anomalies. They tested and evaluated their proposed method based on two datasets.…”

Section: Related Workmentioning

confidence: 99%

“…Nevertheless, most older adults prefer to stay in their own homes for as long as possible rather than in residential or home care facilities to maintain their independence [ 7 , 8 ]. In order to support older adults to live independently in their own homes, the home environments equipped with appropriate sensors, referred to as Intelligent Environments (IE) or Smart Homes (SH), are used to support individuals with their daily activities, improve their quality of life, and allow them to stay safely and independently in their own homes [ 9 , 10 , 11 , 12 ]. To be able to support independent living for older adults, it would be essential to have a means of monitoring to recognise their daily activities and to detect anomalies in the recognised activities.…”

Section: Introductionmentioning

confidence: 99%

An Entropy-Based Approach for Anomaly Detection in Activities of Daily Living in the Presence of a Visitor

Howedi

Lotfi

Pourabdollah

2020

Entropy

View full text Add to dashboard Cite

This paper presents anomaly detection in activities of daily living based on entropy measures. It is shown that the proposed approach will identify anomalies when there are visitors representing a multi-occupant environment. Residents often receive visits from family members or health care workers. Therefore, the residents’ activity is expected to be different when there is a visitor, which could be considered as an abnormal activity pattern. Identifying anomalies is essential for healthcare management, as this will enable action to avoid prospective problems early and to improve and support residents’ ability to live safely and independently in their own homes. Entropy measure analysis is an established method to detect disorder or irregularities in many applications: however, this has rarely been applied in the context of activities of daily living. An experimental evaluation is conducted to detect anomalies obtained from a real home environment. Experimental results are presented to demonstrate the effectiveness of the entropy measures employed in detecting anomalies in the resident’s activity and identifying visiting times in the same environment.

show abstract

“…IDS can be divided into misuse detection and anomaly detection according to the strategies they adopt. Misuse intrusion detection depends on existing pattern database [1] . It analyzes the known attack behaviors, establishes corresponding attack signature database, and then directly detects the attack signatures that have been covered in the pattern database.…”

Section: Introductionmentioning

confidence: 99%

A Review of Intrusion Detection Technology Based on Deep Rein-forcement Learning

Yu¹,

Zhou²,

Wang³

et al. 2021

Electron Sci Technol Appl

View full text Add to dashboard Cite

<p>With the rapid development of modern science and technology, all kinds of network attacks are updated constantly. Therefore, the traditional network security defense mechanism needs to be further improved. Through extensive investigation, this paper presents the latest work of network intrusion detection technology based on deep learning. Firstly, this paper introduces the related concepts of network intrusion detection technology. On this basis, we further evaluate the performance of three common deep learning models in intrusion detection, and conclude that DBN algorithm has some strong advantages. Afterwards, it also puts forward several improvement strategies of intrusion detection models.</p>

show abstract

PUMAD: PU Metric learning for anomaly detection

Cited by 32 publications

References 8 publications

MStream: Fast Anomaly Detection in Multi-Aspect Streams

MStream: Fast Anomaly Detection in Multi-Aspect Streams

An Entropy-Based Approach for Anomaly Detection in Activities of Daily Living in the Presence of a Visitor

A Review of Intrusion Detection Technology Based on Deep Rein-forcement Learning

Contact Info

Product

Resources

About