Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387156851> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4387156851 abstract "One of the most pressing threats to computing systems is software vulnerabilities, which can compromise both hardware and software components. Existing methods for vulnerability detection remain suboptimal. Traditional techniques are both time-consuming and labor-intensive, while machine-learning-based approaches often underperform when applied to complex datasets, due to their inability to capture high-dimensional relationships. Previous deep-learning strategies also fall short in capturing sufficient feature information. Although self-attention mechanisms can process information over long distances, they fail to capture structural information. In this paper, we introduce DefectHunter, an innovative model for vulnerability identification that employs the Conformer mechanism. This mechanism fuses self-attention with convolutional networks to capture both local, position-wise features and global, content-based interactions. Furthermore, we optimize the self-attention mechanisms to mitigate the issue of excessive attention heads introducing extraneous noise by adjusting the denominator. We evaluated DefectHunter against ten baseline methods using six industrial and two highly complex datasets. On the QEMU dataset, DefectHunter exhibited a 20.62% improvement in accuracy over Pongo-70B, and for the CWE-754 dataset, its accuracy was 14.64% higher. To investigate how DefectHunter comprehends vulnerabilities, we conducted a case study, which revealed that our model effectively understands the mechanisms underlying vulnerabilities." @default.
- W4387156851 created "2023-09-30" @default.
- W4387156851 creator A5015083171 @default.
- W4387156851 creator A5018244700 @default.
- W4387156851 creator A5070580609 @default.
- W4387156851 creator A5076313688 @default.
- W4387156851 creator A5084185160 @default.
- W4387156851 date "2023-09-26" @default.
- W4387156851 modified "2023-09-30" @default.
- W4387156851 title "DefectHunter: A Novel LLM-Driven Boosted-Conformer-based Code Vulnerability Detection Mechanism" @default.
- W4387156851 doi "https://doi.org/10.48550/arxiv.2309.15324" @default.
- W4387156851 hasPublicationYear "2023" @default.
- W4387156851 type Work @default.
- W4387156851 citedByCount "0" @default.
- W4387156851 crossrefType "posted-content" @default.
- W4387156851 hasAuthorship W4387156851A5015083171 @default.
- W4387156851 hasAuthorship W4387156851A5018244700 @default.
- W4387156851 hasAuthorship W4387156851A5070580609 @default.
- W4387156851 hasAuthorship W4387156851A5076313688 @default.
- W4387156851 hasAuthorship W4387156851A5084185160 @default.
- W4387156851 hasBestOaLocation W43871568511 @default.
- W4387156851 hasConcept C108583219 @default.
- W4387156851 hasConcept C111472728 @default.
- W4387156851 hasConcept C111919701 @default.
- W4387156851 hasConcept C116834253 @default.
- W4387156851 hasConcept C119857082 @default.
- W4387156851 hasConcept C124101348 @default.
- W4387156851 hasConcept C138885662 @default.
- W4387156851 hasConcept C154945302 @default.
- W4387156851 hasConcept C177264268 @default.
- W4387156851 hasConcept C199360897 @default.
- W4387156851 hasConcept C2776760102 @default.
- W4387156851 hasConcept C2777904410 @default.
- W4387156851 hasConcept C38652104 @default.
- W4387156851 hasConcept C41008148 @default.
- W4387156851 hasConcept C59822182 @default.
- W4387156851 hasConcept C86803240 @default.
- W4387156851 hasConcept C89611455 @default.
- W4387156851 hasConcept C95713431 @default.
- W4387156851 hasConcept C98045186 @default.
- W4387156851 hasConceptScore W4387156851C108583219 @default.
- W4387156851 hasConceptScore W4387156851C111472728 @default.
- W4387156851 hasConceptScore W4387156851C111919701 @default.
- W4387156851 hasConceptScore W4387156851C116834253 @default.
- W4387156851 hasConceptScore W4387156851C119857082 @default.
- W4387156851 hasConceptScore W4387156851C124101348 @default.
- W4387156851 hasConceptScore W4387156851C138885662 @default.
- W4387156851 hasConceptScore W4387156851C154945302 @default.
- W4387156851 hasConceptScore W4387156851C177264268 @default.
- W4387156851 hasConceptScore W4387156851C199360897 @default.
- W4387156851 hasConceptScore W4387156851C2776760102 @default.
- W4387156851 hasConceptScore W4387156851C2777904410 @default.
- W4387156851 hasConceptScore W4387156851C38652104 @default.
- W4387156851 hasConceptScore W4387156851C41008148 @default.
- W4387156851 hasConceptScore W4387156851C59822182 @default.
- W4387156851 hasConceptScore W4387156851C86803240 @default.
- W4387156851 hasConceptScore W4387156851C89611455 @default.
- W4387156851 hasConceptScore W4387156851C95713431 @default.
- W4387156851 hasConceptScore W4387156851C98045186 @default.
- W4387156851 hasLocation W43871568511 @default.
- W4387156851 hasOpenAccess W4387156851 @default.
- W4387156851 hasPrimaryLocation W43871568511 @default.
- W4387156851 hasRelatedWork W2795261237 @default.
- W4387156851 hasRelatedWork W3014300295 @default.
- W4387156851 hasRelatedWork W3164822677 @default.
- W4387156851 hasRelatedWork W4223943233 @default.
- W4387156851 hasRelatedWork W4225161397 @default.
- W4387156851 hasRelatedWork W4312200629 @default.
- W4387156851 hasRelatedWork W4360585206 @default.
- W4387156851 hasRelatedWork W4364306694 @default.
- W4387156851 hasRelatedWork W4380075502 @default.
- W4387156851 hasRelatedWork W4380086463 @default.
- W4387156851 isParatext "false" @default.
- W4387156851 isRetracted "false" @default.
- W4387156851 workType "article" @default.