Matches in SemOpenAlex for { <https://semopenalex.org/work/W2982719286> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2982719286 abstract "Many forms of interaction between computer systems and users are recorded in the form of event records, such as login events, API call records, bank transaction records, etc. These records are often comprised of high-dimensional categorical variables, such as user name, zip code, autonomous system number, etc. In this work, we consider anomaly detection for such data sets, where each record consists of multi-dimensional, potentially very high-cardinality, categorical variables. Our proposed technique, named CADENCE, uses a combination of neural networks, low-dimensional representation learning and noise contrastive estimation. Our approach is based on estimating conditional probability density functions governing observed events, which are assumed to be mostly normal. This conditional modeling approach allows CADENCE to consider each event in its own context, thereby significantly improving its accuracy. We evaluate our proposed method using both synthetic and real world data sets. Our results show that CADENCE performs significantly better than existing methods at real-world anomaly detection tasks." @default.
- W2982719286 created "2019-11-22" @default.
- W2982719286 creator A5025408312 @default.
- W2982719286 creator A5028396045 @default.
- W2982719286 creator A5053106292 @default.
- W2982719286 date "2019-11-11" @default.
- W2982719286 modified "2023-10-05" @default.
- W2982719286 title "CADENCE" @default.
- W2982719286 cites W114517082 @default.
- W2982719286 cites W1973559694 @default.
- W2982719286 cites W1974561058 @default.
- W2982719286 cites W1975570633 @default.
- W2982719286 cites W2000832852 @default.
- W2982719286 cites W2053125529 @default.
- W2982719286 cites W2057117782 @default.
- W2982719286 cites W2067792375 @default.
- W2982719286 cites W2084763720 @default.
- W2982719286 cites W2096793442 @default.
- W2982719286 cites W2103154003 @default.
- W2982719286 cites W2121904442 @default.
- W2982719286 cites W2122646361 @default.
- W2982719286 cites W2134255060 @default.
- W2982719286 cites W2145962650 @default.
- W2982719286 cites W2162774438 @default.
- W2982719286 cites W2250539671 @default.
- W2982719286 cites W2296719434 @default.
- W2982719286 cites W2407044469 @default.
- W2982719286 cites W2509235963 @default.
- W2982719286 cites W2683542543 @default.
- W2982719286 cites W2743138268 @default.
- W2982719286 cites W2767599172 @default.
- W2982719286 cites W2963395938 @default.
- W2982719286 cites W2963932686 @default.
- W2982719286 cites W4234845324 @default.
- W2982719286 doi "https://doi.org/10.1145/3338501.3357368" @default.
- W2982719286 hasPublicationYear "2019" @default.
- W2982719286 type Work @default.
- W2982719286 sameAs 2982719286 @default.
- W2982719286 citedByCount "2" @default.
- W2982719286 countsByYear W29827192862022 @default.
- W2982719286 crossrefType "proceedings-article" @default.
- W2982719286 hasAuthorship W2982719286A5025408312 @default.
- W2982719286 hasAuthorship W2982719286A5028396045 @default.
- W2982719286 hasAuthorship W2982719286A5053106292 @default.
- W2982719286 hasConcept C127413603 @default.
- W2982719286 hasConcept C24326235 @default.
- W2982719286 hasConcept C2777125575 @default.
- W2982719286 hasConcept C41008148 @default.
- W2982719286 hasConceptScore W2982719286C127413603 @default.
- W2982719286 hasConceptScore W2982719286C24326235 @default.
- W2982719286 hasConceptScore W2982719286C2777125575 @default.
- W2982719286 hasConceptScore W2982719286C41008148 @default.
- W2982719286 hasLocation W29827192861 @default.
- W2982719286 hasOpenAccess W2982719286 @default.
- W2982719286 hasPrimaryLocation W29827192861 @default.
- W2982719286 hasRelatedWork W1964447062 @default.
- W2982719286 hasRelatedWork W2017012638 @default.
- W2982719286 hasRelatedWork W2065850627 @default.
- W2982719286 hasRelatedWork W2071885361 @default.
- W2982719286 hasRelatedWork W2088265144 @default.
- W2982719286 hasRelatedWork W2138282914 @default.
- W2982719286 hasRelatedWork W2748952813 @default.
- W2982719286 hasRelatedWork W2899084033 @default.
- W2982719286 hasRelatedWork W3186427148 @default.
- W2982719286 hasRelatedWork W4289538008 @default.
- W2982719286 isParatext "false" @default.
- W2982719286 isRetracted "false" @default.
- W2982719286 magId "2982719286" @default.
- W2982719286 workType "article" @default.