Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2203.16331 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915523147595776 |
|---|---|
| author | Verwer, Sicco Hammerschmidt, Christian |
| author_facet | Verwer, Sicco Hammerschmidt, Christian |
| contents | We present the efficient implementations of probabilistic deterministic finite automaton learning methods available in FlexFringe. These implement well-known strategies for state-merging including several modifications to improve their performance in practice. We show experimentally that these algorithms obtain competitive results and significant improvements over a default implementation. We also demonstrate how to use FlexFringe to learn interpretable models from software logs and use these for anomaly detection. Although less interpretable, we show that learning smaller more convoluted models improves the performance of FlexFringe on anomaly detection, outperforming an existing solution based on neural nets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_16331 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | FlexFringe: Modeling Software Behavior by Learning Probabilistic Automata Verwer, Sicco Hammerschmidt, Christian Machine Learning Logic in Computer Science Software Engineering We present the efficient implementations of probabilistic deterministic finite automaton learning methods available in FlexFringe. These implement well-known strategies for state-merging including several modifications to improve their performance in practice. We show experimentally that these algorithms obtain competitive results and significant improvements over a default implementation. We also demonstrate how to use FlexFringe to learn interpretable models from software logs and use these for anomaly detection. Although less interpretable, we show that learning smaller more convoluted models improves the performance of FlexFringe on anomaly detection, outperforming an existing solution based on neural nets. |
| title | FlexFringe: Modeling Software Behavior by Learning Probabilistic Automata |
| topic | Machine Learning Logic in Computer Science Software Engineering |
| url | https://arxiv.org/abs/2203.16331 |