Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378189129> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4378189129 endingPage "110389" @default.
- W4378189129 startingPage "110389" @default.
- W4378189129 abstract "Backdoor attacks targeting the deep neural network are flourishing recently and are more stealthy than existing adversarial attacks. A deep understanding of the backdoor attacks targeting malware detection models is still missing. We design a highly transferable backdoor attack targeting three benchmark convolutional neural networks (CNNs) for malware detection. The designed backdoor attack involves two steps: trigger generation and trigger insertion. Firstly, based on the computation of the most significant byte sub-sequence from samples of a chosen target label, the trigger patterns are generated by training a class activation mapping-based deep neural network (CAM-DNN). Then, the byte sequence with the maximum class activation mapping score is chosen as the candidate trigger pattern. The computed trigger pattern is then inserted into an index-based place that satisfies the minimum distance between a predefined feature space to the target label. Through detailed experiments, the CAM-DNN-based backdoor considers many influential factors, including the number of backdoor triggers, the degree of perturbations applied on a single trigger pattern, the length of the inserted trigger, etc. The experiments demonstrate that the CAM-DNN-based backdoor attack achieves an 89.58% success rate on average at the cost of a 2.25% accuracy drop on clean inputs. More importantly, the poisoned malware ensures high integrity because the original malicious functions are preserved to a large extent." @default.
- W4378189129 created "2023-05-26" @default.
- W4378189129 creator A5000436275 @default.
- W4378189129 creator A5009669605 @default.
- W4378189129 creator A5036803265 @default.
- W4378189129 creator A5045752561 @default.
- W4378189129 creator A5072479287 @default.
- W4378189129 date "2023-08-01" @default.
- W4378189129 modified "2023-10-18" @default.
- W4378189129 title "Universal backdoor attack on deep neural networks for malware detection" @default.
- W4378189129 cites W2060537671 @default.
- W4378189129 cites W2295107390 @default.
- W4378189129 cites W2406556600 @default.
- W4378189129 cites W2732916693 @default.
- W4378189129 cites W2753783305 @default.
- W4378189129 cites W2780061022 @default.
- W4378189129 cites W2807363941 @default.
- W4378189129 cites W2942091739 @default.
- W4378189129 cites W2945645805 @default.
- W4378189129 cites W2963165251 @default.
- W4378189129 cites W2966342255 @default.
- W4378189129 cites W2973628901 @default.
- W4378189129 cites W3007264885 @default.
- W4378189129 cites W3090898103 @default.
- W4378189129 cites W3104141960 @default.
- W4378189129 cites W3164220323 @default.
- W4378189129 cites W3170962599 @default.
- W4378189129 cites W3196546979 @default.
- W4378189129 cites W3212158867 @default.
- W4378189129 cites W4200031816 @default.
- W4378189129 cites W4206776436 @default.
- W4378189129 cites W4285233920 @default.
- W4378189129 cites W4311852625 @default.
- W4378189129 cites W4312700692 @default.
- W4378189129 doi "https://doi.org/10.1016/j.asoc.2023.110389" @default.
- W4378189129 hasPublicationYear "2023" @default.
- W4378189129 type Work @default.
- W4378189129 citedByCount "0" @default.
- W4378189129 crossrefType "journal-article" @default.
- W4378189129 hasAuthorship W4378189129A5000436275 @default.
- W4378189129 hasAuthorship W4378189129A5009669605 @default.
- W4378189129 hasAuthorship W4378189129A5036803265 @default.
- W4378189129 hasAuthorship W4378189129A5045752561 @default.
- W4378189129 hasAuthorship W4378189129A5072479287 @default.
- W4378189129 hasConcept C108583219 @default.
- W4378189129 hasConcept C111919701 @default.
- W4378189129 hasConcept C153180895 @default.
- W4378189129 hasConcept C154945302 @default.
- W4378189129 hasConcept C2781045450 @default.
- W4378189129 hasConcept C38652104 @default.
- W4378189129 hasConcept C41008148 @default.
- W4378189129 hasConcept C43364308 @default.
- W4378189129 hasConcept C50644808 @default.
- W4378189129 hasConcept C541664917 @default.
- W4378189129 hasConcept C81363708 @default.
- W4378189129 hasConceptScore W4378189129C108583219 @default.
- W4378189129 hasConceptScore W4378189129C111919701 @default.
- W4378189129 hasConceptScore W4378189129C153180895 @default.
- W4378189129 hasConceptScore W4378189129C154945302 @default.
- W4378189129 hasConceptScore W4378189129C2781045450 @default.
- W4378189129 hasConceptScore W4378189129C38652104 @default.
- W4378189129 hasConceptScore W4378189129C41008148 @default.
- W4378189129 hasConceptScore W4378189129C43364308 @default.
- W4378189129 hasConceptScore W4378189129C50644808 @default.
- W4378189129 hasConceptScore W4378189129C541664917 @default.
- W4378189129 hasConceptScore W4378189129C81363708 @default.
- W4378189129 hasLocation W43781891291 @default.
- W4378189129 hasOpenAccess W4378189129 @default.
- W4378189129 hasPrimaryLocation W43781891291 @default.
- W4378189129 hasRelatedWork W2731899572 @default.
- W4378189129 hasRelatedWork W2999805992 @default.
- W4378189129 hasRelatedWork W3011074480 @default.
- W4378189129 hasRelatedWork W3116150086 @default.
- W4378189129 hasRelatedWork W3133861977 @default.
- W4378189129 hasRelatedWork W3192840557 @default.
- W4378189129 hasRelatedWork W4200173597 @default.
- W4378189129 hasRelatedWork W4291897433 @default.
- W4378189129 hasRelatedWork W4312417841 @default.
- W4378189129 hasRelatedWork W4321369474 @default.
- W4378189129 hasVolume "143" @default.
- W4378189129 isParatext "false" @default.
- W4378189129 isRetracted "false" @default.
- W4378189129 workType "article" @default.