Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285110406> ?p ?o ?g. }
- W4285110406 endingPage "2308" @default.
- W4285110406 startingPage "2295" @default.
- W4285110406 abstract "Machine learning based network intrusion system (NIDS) is known to be vulnerable to evasions. Attackers conceal intrusion activities to make them undetected. Researching evasion techniques contributes to evaluating and increasing the robustness of NIDS. Previous evasion approaches modify feature values or packets of an offline network trace as a whole. However, in real scenarios, attackers are constrained to manipulate only outbound packets on the fly. To bridge this assumption gap, we present the first evasion solution for live network traffic against learning based NIDSs. The solution consists of three components: a devised Kalman filter based algorithm to predicate the feature values of live flows, a set of formally constructed atomic packet mutation operators, and a proposed Strength Enhanced Deep Q-learning (SE-DQN) to determine effective mutation operators on outbound packets according to the predicted features. A defense scheme based on adaptive decision threshold adjustment is also provided. Experimental evaluation is presented on various NIDS classifiers and cyber attacks. Results show that SE-DQN achieves an evasion rate of at least 64.2% on most classifiers and even more than 90% on certain ones, and it is three times faster than DQN on learning mutation policy. The defense scheme shows an improvement of at least 76.4% on recall measurement." @default.
- W4285110406 created "2022-07-14" @default.
- W4285110406 creator A5022611612 @default.
- W4285110406 creator A5040006297 @default.
- W4285110406 creator A5052605149 @default.
- W4285110406 creator A5059567156 @default.
- W4285110406 date "2022-09-01" @default.
- W4285110406 modified "2023-10-18" @default.
- W4285110406 title "Sneaking Through Security: Mutating Live Network Traffic to Evade Learning-Based NIDS" @default.
- W4285110406 cites W1481573196 @default.
- W4285110406 cites W1985902740 @default.
- W4285110406 cites W2012210084 @default.
- W4285110406 cites W2026258420 @default.
- W4285110406 cites W2152575748 @default.
- W4285110406 cites W2155300758 @default.
- W4285110406 cites W2170316384 @default.
- W4285110406 cites W2537766808 @default.
- W4285110406 cites W2588675103 @default.
- W4285110406 cites W2766612868 @default.
- W4285110406 cites W2783320270 @default.
- W4285110406 cites W2839900884 @default.
- W4285110406 cites W2886533716 @default.
- W4285110406 cites W2897256107 @default.
- W4285110406 cites W2898318153 @default.
- W4285110406 cites W2904539465 @default.
- W4285110406 cites W2907236248 @default.
- W4285110406 cites W2908449057 @default.
- W4285110406 cites W2912711574 @default.
- W4285110406 cites W2914899172 @default.
- W4285110406 cites W2921434519 @default.
- W4285110406 cites W2924689635 @default.
- W4285110406 cites W2959169310 @default.
- W4285110406 cites W2963197901 @default.
- W4285110406 cites W2963391384 @default.
- W4285110406 cites W2964210735 @default.
- W4285110406 cites W2981880399 @default.
- W4285110406 cites W3009195050 @default.
- W4285110406 cites W3010612350 @default.
- W4285110406 cites W3015248254 @default.
- W4285110406 cites W3017217726 @default.
- W4285110406 cites W3032638893 @default.
- W4285110406 cites W3035366542 @default.
- W4285110406 cites W3045016378 @default.
- W4285110406 cites W3102091066 @default.
- W4285110406 cites W3104735167 @default.
- W4285110406 cites W3111088413 @default.
- W4285110406 cites W3111390419 @default.
- W4285110406 cites W3115360974 @default.
- W4285110406 cites W3134894590 @default.
- W4285110406 cites W2793756773 @default.
- W4285110406 doi "https://doi.org/10.1109/tnsm.2022.3173933" @default.
- W4285110406 hasPublicationYear "2022" @default.
- W4285110406 type Work @default.
- W4285110406 citedByCount "0" @default.
- W4285110406 crossrefType "journal-article" @default.
- W4285110406 hasAuthorship W4285110406A5022611612 @default.
- W4285110406 hasAuthorship W4285110406A5040006297 @default.
- W4285110406 hasAuthorship W4285110406A5052605149 @default.
- W4285110406 hasAuthorship W4285110406A5059567156 @default.
- W4285110406 hasConcept C104317684 @default.
- W4285110406 hasConcept C119857082 @default.
- W4285110406 hasConcept C154945302 @default.
- W4285110406 hasConcept C158379750 @default.
- W4285110406 hasConcept C182590292 @default.
- W4285110406 hasConcept C185592680 @default.
- W4285110406 hasConcept C203014093 @default.
- W4285110406 hasConcept C2781251061 @default.
- W4285110406 hasConcept C35525427 @default.
- W4285110406 hasConcept C38652104 @default.
- W4285110406 hasConcept C41008148 @default.
- W4285110406 hasConcept C55493867 @default.
- W4285110406 hasConcept C63479239 @default.
- W4285110406 hasConcept C86803240 @default.
- W4285110406 hasConcept C8891405 @default.
- W4285110406 hasConceptScore W4285110406C104317684 @default.
- W4285110406 hasConceptScore W4285110406C119857082 @default.
- W4285110406 hasConceptScore W4285110406C154945302 @default.
- W4285110406 hasConceptScore W4285110406C158379750 @default.
- W4285110406 hasConceptScore W4285110406C182590292 @default.
- W4285110406 hasConceptScore W4285110406C185592680 @default.
- W4285110406 hasConceptScore W4285110406C203014093 @default.
- W4285110406 hasConceptScore W4285110406C2781251061 @default.
- W4285110406 hasConceptScore W4285110406C35525427 @default.
- W4285110406 hasConceptScore W4285110406C38652104 @default.
- W4285110406 hasConceptScore W4285110406C41008148 @default.
- W4285110406 hasConceptScore W4285110406C55493867 @default.
- W4285110406 hasConceptScore W4285110406C63479239 @default.
- W4285110406 hasConceptScore W4285110406C86803240 @default.
- W4285110406 hasConceptScore W4285110406C8891405 @default.
- W4285110406 hasFunder F4320333334 @default.
- W4285110406 hasFunder F4320336567 @default.
- W4285110406 hasIssue "3" @default.
- W4285110406 hasLocation W42851104061 @default.
- W4285110406 hasOpenAccess W4285110406 @default.
- W4285110406 hasPrimaryLocation W42851104061 @default.
- W4285110406 hasRelatedWork W1548771250 @default.
- W4285110406 hasRelatedWork W1977863481 @default.
- W4285110406 hasRelatedWork W1992118813 @default.