Matches in SemOpenAlex for { <https://semopenalex.org/work/W3180933073> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3180933073 endingPage "37" @default.
- W3180933073 startingPage "20" @default.
- W3180933073 abstract "Malware designers have become increasingly sophisticated over time, crafting polymorphic and metamorphic malware employing obfuscation tricks such as packing and encryption to evade signature-based malware detection systems. Therefore, security professionals use machine learning-based systems to toughen their defenses – based on malware’s dynamic behavioral features. However, these systems are susceptible to adversarial inputs. Some malware designers exploit this vulnerability to bypass detection. In this work, we develop two approaches to evade machine learning-based classifiers. First, we create a Generative Adversarial Networks (GAN) based method, which we call ‘Malware Evasion using GAN’ (MEGAN) and the extended version ‘Malware Evasion using GAN with Reduced Perturbation (MEGAN-RP).’ Second, we develop a novel reinforcement learning-based approach called ‘Malware Evasion using Reinforcement Agent (MERA).’ We generate adversarial malware that simultaneously minimizes the recall of a target classifier and the amount of perturbation needed in the actual malware to evade detection. We evaluate our work against 13 different BlackBox detection models – all of which use dynamic presence-absence of API calls as features. We observe that our approaches reduce the recall of almost all BlackBox models to zero. Further, MERA outperforms all the other models and reduces True Positive Rate (TPR) to zero against all target models except the Decision Tree (DT) – with minimum perturbation in 6 out of 13 target models. We also present experimental results on adversarial retraining defense and its evasion for GAN based strategies." @default.
- W3180933073 created "2021-07-19" @default.
- W3180933073 creator A5021517996 @default.
- W3180933073 creator A5030815901 @default.
- W3180933073 creator A5033663758 @default.
- W3180933073 creator A5063600287 @default.
- W3180933073 date "2021-01-01" @default.
- W3180933073 modified "2023-09-27" @default.
- W3180933073 title "Adversaries Strike Hard: Adversarial Attacks Against Malware Classifiers Using Dynamic API Calls as Features" @default.
- W3180933073 cites W1587106557 @default.
- W3180933073 cites W2141278204 @default.
- W3180933073 cites W2498119267 @default.
- W3180933073 cites W2543927648 @default.
- W3180933073 cites W2603766943 @default.
- W3180933073 cites W2911964244 @default.
- W3180933073 cites W2932977083 @default.
- W3180933073 cites W2964082701 @default.
- W3180933073 cites W3006837754 @default.
- W3180933073 cites W3093077017 @default.
- W3180933073 doi "https://doi.org/10.1007/978-3-030-78086-9_2" @default.
- W3180933073 hasPublicationYear "2021" @default.
- W3180933073 type Work @default.
- W3180933073 sameAs 3180933073 @default.
- W3180933073 citedByCount "1" @default.
- W3180933073 countsByYear W31809330732023 @default.
- W3180933073 crossrefType "book-chapter" @default.
- W3180933073 hasAuthorship W3180933073A5021517996 @default.
- W3180933073 hasAuthorship W3180933073A5030815901 @default.
- W3180933073 hasAuthorship W3180933073A5033663758 @default.
- W3180933073 hasAuthorship W3180933073A5063600287 @default.
- W3180933073 hasConcept C111919701 @default.
- W3180933073 hasConcept C119857082 @default.
- W3180933073 hasConcept C154945302 @default.
- W3180933073 hasConcept C165696696 @default.
- W3180933073 hasConcept C203014093 @default.
- W3180933073 hasConcept C2778579508 @default.
- W3180933073 hasConcept C2781251061 @default.
- W3180933073 hasConcept C37736160 @default.
- W3180933073 hasConcept C38652104 @default.
- W3180933073 hasConcept C40305131 @default.
- W3180933073 hasConcept C41008148 @default.
- W3180933073 hasConcept C541664917 @default.
- W3180933073 hasConcept C84525096 @default.
- W3180933073 hasConcept C86803240 @default.
- W3180933073 hasConcept C8891405 @default.
- W3180933073 hasConcept C95623464 @default.
- W3180933073 hasConcept C97541855 @default.
- W3180933073 hasConceptScore W3180933073C111919701 @default.
- W3180933073 hasConceptScore W3180933073C119857082 @default.
- W3180933073 hasConceptScore W3180933073C154945302 @default.
- W3180933073 hasConceptScore W3180933073C165696696 @default.
- W3180933073 hasConceptScore W3180933073C203014093 @default.
- W3180933073 hasConceptScore W3180933073C2778579508 @default.
- W3180933073 hasConceptScore W3180933073C2781251061 @default.
- W3180933073 hasConceptScore W3180933073C37736160 @default.
- W3180933073 hasConceptScore W3180933073C38652104 @default.
- W3180933073 hasConceptScore W3180933073C40305131 @default.
- W3180933073 hasConceptScore W3180933073C41008148 @default.
- W3180933073 hasConceptScore W3180933073C541664917 @default.
- W3180933073 hasConceptScore W3180933073C84525096 @default.
- W3180933073 hasConceptScore W3180933073C86803240 @default.
- W3180933073 hasConceptScore W3180933073C8891405 @default.
- W3180933073 hasConceptScore W3180933073C95623464 @default.
- W3180933073 hasConceptScore W3180933073C97541855 @default.
- W3180933073 hasLocation W31809330731 @default.
- W3180933073 hasOpenAccess W3180933073 @default.
- W3180933073 hasPrimaryLocation W31809330731 @default.
- W3180933073 hasRelatedWork W2289453476 @default.
- W3180933073 hasRelatedWork W2470029541 @default.
- W3180933073 hasRelatedWork W2470502009 @default.
- W3180933073 hasRelatedWork W2582087290 @default.
- W3180933073 hasRelatedWork W2900235625 @default.
- W3180933073 hasRelatedWork W3131233328 @default.
- W3180933073 hasRelatedWork W3195170298 @default.
- W3180933073 hasRelatedWork W3204946594 @default.
- W3180933073 hasRelatedWork W4311731381 @default.
- W3180933073 hasRelatedWork W4386041582 @default.
- W3180933073 isParatext "false" @default.
- W3180933073 isRetracted "false" @default.
- W3180933073 magId "3180933073" @default.
- W3180933073 workType "book-chapter" @default.