Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296564804> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4296564804 abstract "Many challenging real-world problems require the deployment of ensembles multiple complementary learning models to reach acceptable performance levels. While effective, applying the entire ensemble to every sample is costly and often unnecessary. Deep Reinforcement Learning (DRL) offers a cost-effective alternative, where detectors are dynamically chosen based on the output of their predecessors, with their usefulness weighted against their computational cost. Despite their potential, DRL-based solutions are not widely used in this capacity, partly due to the difficulties in configuring the reward function for each new task, the unpredictable reactions of the DRL agent to changes in the data, and the inability to use common performance metrics (e.g., TPR/FPR) to guide the algorithm's performance. In this study we propose methods for fine-tuning and calibrating DRL-based policies so that they can meet multiple performance goals. Moreover, we present a method for transferring effective security policies from one dataset to another. Finally, we demonstrate that our approach is highly robust against adversarial attacks." @default.
- W4296564804 created "2022-09-21" @default.
- W4296564804 creator A5002391103 @default.
- W4296564804 creator A5044390999 @default.
- W4296564804 creator A5088176604 @default.
- W4296564804 date "2022-09-19" @default.
- W4296564804 modified "2023-10-16" @default.
- W4296564804 title "A Transferable and Automatic Tuning of Deep Reinforcement Learning for Cost Effective Phishing Detection" @default.
- W4296564804 doi "https://doi.org/10.48550/arxiv.2209.09033" @default.
- W4296564804 hasPublicationYear "2022" @default.
- W4296564804 type Work @default.
- W4296564804 citedByCount "0" @default.
- W4296564804 crossrefType "posted-content" @default.
- W4296564804 hasAuthorship W4296564804A5002391103 @default.
- W4296564804 hasAuthorship W4296564804A5044390999 @default.
- W4296564804 hasAuthorship W4296564804A5088176604 @default.
- W4296564804 hasBestOaLocation W42965648041 @default.
- W4296564804 hasConcept C105339364 @default.
- W4296564804 hasConcept C111919701 @default.
- W4296564804 hasConcept C119857082 @default.
- W4296564804 hasConcept C127413603 @default.
- W4296564804 hasConcept C14036430 @default.
- W4296564804 hasConcept C154945302 @default.
- W4296564804 hasConcept C185592680 @default.
- W4296564804 hasConcept C198531522 @default.
- W4296564804 hasConcept C201995342 @default.
- W4296564804 hasConcept C2780451532 @default.
- W4296564804 hasConcept C37736160 @default.
- W4296564804 hasConcept C41008148 @default.
- W4296564804 hasConcept C43617362 @default.
- W4296564804 hasConcept C78458016 @default.
- W4296564804 hasConcept C86803240 @default.
- W4296564804 hasConcept C97541855 @default.
- W4296564804 hasConceptScore W4296564804C105339364 @default.
- W4296564804 hasConceptScore W4296564804C111919701 @default.
- W4296564804 hasConceptScore W4296564804C119857082 @default.
- W4296564804 hasConceptScore W4296564804C127413603 @default.
- W4296564804 hasConceptScore W4296564804C14036430 @default.
- W4296564804 hasConceptScore W4296564804C154945302 @default.
- W4296564804 hasConceptScore W4296564804C185592680 @default.
- W4296564804 hasConceptScore W4296564804C198531522 @default.
- W4296564804 hasConceptScore W4296564804C201995342 @default.
- W4296564804 hasConceptScore W4296564804C2780451532 @default.
- W4296564804 hasConceptScore W4296564804C37736160 @default.
- W4296564804 hasConceptScore W4296564804C41008148 @default.
- W4296564804 hasConceptScore W4296564804C43617362 @default.
- W4296564804 hasConceptScore W4296564804C78458016 @default.
- W4296564804 hasConceptScore W4296564804C86803240 @default.
- W4296564804 hasConceptScore W4296564804C97541855 @default.
- W4296564804 hasLocation W42965648041 @default.
- W4296564804 hasOpenAccess W4296564804 @default.
- W4296564804 hasPrimaryLocation W42965648041 @default.
- W4296564804 hasRelatedWork W2734912394 @default.
- W4296564804 hasRelatedWork W2891191051 @default.
- W4296564804 hasRelatedWork W2990162188 @default.
- W4296564804 hasRelatedWork W3013360982 @default.
- W4296564804 hasRelatedWork W3022038857 @default.
- W4296564804 hasRelatedWork W3131296902 @default.
- W4296564804 hasRelatedWork W3145910327 @default.
- W4296564804 hasRelatedWork W4287598984 @default.
- W4296564804 hasRelatedWork W4289860834 @default.
- W4296564804 hasRelatedWork W4319083788 @default.
- W4296564804 isParatext "false" @default.
- W4296564804 isRetracted "false" @default.
- W4296564804 workType "article" @default.