Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385412175> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4385412175 abstract "Anomaly detection in Multivariate Time-Series (MTS) data plays an important role in multiple domains, especially in cybersecurity, for the detection of unknown attacks. DC- VAE is a recent approach we have proposed for anomaly detection in network measurement multivariate data, which uses Variational Auto Encoders (VAEs) and Dilated Convolutional Neural Networks (DCNNs) to model complex and high-dimensional MTS data. However, detecting anomalies using VAEs can result in performance degradation and even catastrophic forgetting when trained on dynamic and evolving network measurements, particularly in the event of concept drifts. We extend DC- VAE to a continual learning setup, leveraging the generative AI properties of the underlying models to deal with continually evolving data. We introduce GenDeX, an approach to Generative AI-based anomaly detection which compresses the patterns extracted from past measurements into a generative model that can synthesize MTS data out of input Gaussian noise, mimicking the characteristics of the MTS data used for training. GenDeX relies on a Deep Generative Replay paradigm to realize continual learning, combining synthesized past MTS measurements with new observations to update the detection model. Using a large-scale, multi-dimensional network monitoring dataset collected from an operational mobile Internet Service Provider (ISP), we showcase the functionality of DC-VAE in the event of concept drifts, and study in-depth its generative characteristics, assessing GenDeX synthetically generated MTS examples. GenDeX enables DC- VAE adapting to continually evolving data, overcoming the limitations of catastrophic forgetting." @default.
- W4385412175 created "2023-08-01" @default.
- W4385412175 creator A5000877972 @default.
- W4385412175 creator A5081556750 @default.
- W4385412175 creator A5085313807 @default.
- W4385412175 date "2023-07-01" @default.
- W4385412175 modified "2023-10-10" @default.
- W4385412175 title "Fake it till you Detect it: Continual Anomaly Detection in Multivariate Time-Series using Generative AI" @default.
- W4385412175 cites W2122646361 @default.
- W4385412175 cites W2278186031 @default.
- W4385412175 cites W2407991977 @default.
- W4385412175 cites W2542991588 @default.
- W4385412175 cites W2911200746 @default.
- W4385412175 cites W3035311645 @default.
- W4385412175 cites W3136173905 @default.
- W4385412175 cites W3152030785 @default.
- W4385412175 cites W3160228379 @default.
- W4385412175 cites W4211139099 @default.
- W4385412175 cites W4283659112 @default.
- W4385412175 cites W4307020421 @default.
- W4385412175 doi "https://doi.org/10.1109/eurospw59978.2023.00068" @default.
- W4385412175 hasPublicationYear "2023" @default.
- W4385412175 type Work @default.
- W4385412175 citedByCount "0" @default.
- W4385412175 crossrefType "proceedings-article" @default.
- W4385412175 hasAuthorship W4385412175A5000877972 @default.
- W4385412175 hasAuthorship W4385412175A5081556750 @default.
- W4385412175 hasAuthorship W4385412175A5085313807 @default.
- W4385412175 hasConcept C108583219 @default.
- W4385412175 hasConcept C119857082 @default.
- W4385412175 hasConcept C121332964 @default.
- W4385412175 hasConcept C124101348 @default.
- W4385412175 hasConcept C138885662 @default.
- W4385412175 hasConcept C151406439 @default.
- W4385412175 hasConcept C154945302 @default.
- W4385412175 hasConcept C167966045 @default.
- W4385412175 hasConcept C2779662365 @default.
- W4385412175 hasConcept C39890363 @default.
- W4385412175 hasConcept C41008148 @default.
- W4385412175 hasConcept C41895202 @default.
- W4385412175 hasConcept C62520636 @default.
- W4385412175 hasConcept C7149132 @default.
- W4385412175 hasConcept C739882 @default.
- W4385412175 hasConcept C81363708 @default.
- W4385412175 hasConceptScore W4385412175C108583219 @default.
- W4385412175 hasConceptScore W4385412175C119857082 @default.
- W4385412175 hasConceptScore W4385412175C121332964 @default.
- W4385412175 hasConceptScore W4385412175C124101348 @default.
- W4385412175 hasConceptScore W4385412175C138885662 @default.
- W4385412175 hasConceptScore W4385412175C151406439 @default.
- W4385412175 hasConceptScore W4385412175C154945302 @default.
- W4385412175 hasConceptScore W4385412175C167966045 @default.
- W4385412175 hasConceptScore W4385412175C2779662365 @default.
- W4385412175 hasConceptScore W4385412175C39890363 @default.
- W4385412175 hasConceptScore W4385412175C41008148 @default.
- W4385412175 hasConceptScore W4385412175C41895202 @default.
- W4385412175 hasConceptScore W4385412175C62520636 @default.
- W4385412175 hasConceptScore W4385412175C7149132 @default.
- W4385412175 hasConceptScore W4385412175C739882 @default.
- W4385412175 hasConceptScore W4385412175C81363708 @default.
- W4385412175 hasLocation W43854121751 @default.
- W4385412175 hasOpenAccess W4385412175 @default.
- W4385412175 hasPrimaryLocation W43854121751 @default.
- W4385412175 hasRelatedWork W2731899572 @default.
- W4385412175 hasRelatedWork W2999805992 @default.
- W4385412175 hasRelatedWork W3116150086 @default.
- W4385412175 hasRelatedWork W3133861977 @default.
- W4385412175 hasRelatedWork W4200173597 @default.
- W4385412175 hasRelatedWork W4285195761 @default.
- W4385412175 hasRelatedWork W4291897433 @default.
- W4385412175 hasRelatedWork W4312417841 @default.
- W4385412175 hasRelatedWork W4321369474 @default.
- W4385412175 hasRelatedWork W4380075502 @default.
- W4385412175 isParatext "false" @default.
- W4385412175 isRetracted "false" @default.
- W4385412175 workType "article" @default.