Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296881042> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4296881042 endingPage "444" @default.
- W4296881042 startingPage "425" @default.
- W4296881042 abstract "The training and development of good deep learning models is often a challenging task, thus leading individuals (developers, researchers, and practitioners alike) to use third-party models residing in public repositories, fine-tuning these models to their needs usually with little-to-no effort. Despite its undeniable benefits, this practice can lead to new attack vectors. In this paper, we demonstrate the feasibility and effectiveness of one such attack, namely malware embedding in deep learning models. We push the boundaries of current state-of-the-art by introducing MaleficNet, a technique that combines spread-spectrum channel coding with error correction techniques, injecting malicious payloads in the parameters of deep neural networks, all while causing no degradation to the model’s performance and successfully bypassing state-of-the-art detection and removal mechanisms. We believe this work will raise awareness against these new, dangerous, camouflaged threats, assist the research community and practitioners in evaluating the capabilities of modern machine learning architectures, and pave the way to research targeting the detection and mitigation of such threats." @default.
- W4296881042 created "2022-09-24" @default.
- W4296881042 creator A5046905749 @default.
- W4296881042 creator A5068361533 @default.
- W4296881042 creator A5080694735 @default.
- W4296881042 creator A5083399524 @default.
- W4296881042 creator A5088555568 @default.
- W4296881042 date "2022-01-01" @default.
- W4296881042 modified "2023-10-01" @default.
- W4296881042 title "MaleficNet: Hiding Malware into Deep Neural Networks Using Spread-Spectrum Channel Coding" @default.
- W4296881042 cites W1536930200 @default.
- W4296881042 cites W1849277567 @default.
- W4296881042 cites W2003010976 @default.
- W4296881042 cites W2028197392 @default.
- W4296881042 cites W2081825044 @default.
- W4296881042 cites W2108598243 @default.
- W4296881042 cites W2143612262 @default.
- W4296881042 cites W2147768505 @default.
- W4296881042 cites W2170371953 @default.
- W4296881042 cites W2194775991 @default.
- W4296881042 cites W2531409750 @default.
- W4296881042 cites W2807363941 @default.
- W4296881042 cites W2942091739 @default.
- W4296881042 cites W2962835266 @default.
- W4296881042 cites W2963446712 @default.
- W4296881042 cites W2963532563 @default.
- W4296881042 cites W2973202379 @default.
- W4296881042 cites W3111614445 @default.
- W4296881042 cites W3149815788 @default.
- W4296881042 cites W3199673641 @default.
- W4296881042 cites W3212298803 @default.
- W4296881042 cites W347692644 @default.
- W4296881042 cites W4205480242 @default.
- W4296881042 cites W4211132239 @default.
- W4296881042 cites W4220737740 @default.
- W4296881042 cites W4285361214 @default.
- W4296881042 cites W4287849804 @default.
- W4296881042 cites W4287887285 @default.
- W4296881042 doi "https://doi.org/10.1007/978-3-031-17143-7_21" @default.
- W4296881042 hasPublicationYear "2022" @default.
- W4296881042 type Work @default.
- W4296881042 citedByCount "0" @default.
- W4296881042 crossrefType "book-chapter" @default.
- W4296881042 hasAuthorship W4296881042A5046905749 @default.
- W4296881042 hasAuthorship W4296881042A5068361533 @default.
- W4296881042 hasAuthorship W4296881042A5080694735 @default.
- W4296881042 hasAuthorship W4296881042A5083399524 @default.
- W4296881042 hasAuthorship W4296881042A5088555568 @default.
- W4296881042 hasConcept C105795698 @default.
- W4296881042 hasConcept C108583219 @default.
- W4296881042 hasConcept C119857082 @default.
- W4296881042 hasConcept C154945302 @default.
- W4296881042 hasConcept C179518139 @default.
- W4296881042 hasConcept C2522767166 @default.
- W4296881042 hasConcept C2984842247 @default.
- W4296881042 hasConcept C33923547 @default.
- W4296881042 hasConcept C38652104 @default.
- W4296881042 hasConcept C41008148 @default.
- W4296881042 hasConcept C41608201 @default.
- W4296881042 hasConcept C50644808 @default.
- W4296881042 hasConcept C541664917 @default.
- W4296881042 hasConceptScore W4296881042C105795698 @default.
- W4296881042 hasConceptScore W4296881042C108583219 @default.
- W4296881042 hasConceptScore W4296881042C119857082 @default.
- W4296881042 hasConceptScore W4296881042C154945302 @default.
- W4296881042 hasConceptScore W4296881042C179518139 @default.
- W4296881042 hasConceptScore W4296881042C2522767166 @default.
- W4296881042 hasConceptScore W4296881042C2984842247 @default.
- W4296881042 hasConceptScore W4296881042C33923547 @default.
- W4296881042 hasConceptScore W4296881042C38652104 @default.
- W4296881042 hasConceptScore W4296881042C41008148 @default.
- W4296881042 hasConceptScore W4296881042C41608201 @default.
- W4296881042 hasConceptScore W4296881042C50644808 @default.
- W4296881042 hasConceptScore W4296881042C541664917 @default.
- W4296881042 hasLocation W42968810421 @default.
- W4296881042 hasOpenAccess W4296881042 @default.
- W4296881042 hasPrimaryLocation W42968810421 @default.
- W4296881042 hasRelatedWork W2942650110 @default.
- W4296881042 hasRelatedWork W2950066684 @default.
- W4296881042 hasRelatedWork W2952919291 @default.
- W4296881042 hasRelatedWork W2968586400 @default.
- W4296881042 hasRelatedWork W3082895349 @default.
- W4296881042 hasRelatedWork W3179488938 @default.
- W4296881042 hasRelatedWork W4288853838 @default.
- W4296881042 hasRelatedWork W4298388782 @default.
- W4296881042 hasRelatedWork W4312831135 @default.
- W4296881042 hasRelatedWork W4316087074 @default.
- W4296881042 isParatext "false" @default.
- W4296881042 isRetracted "false" @default.
- W4296881042 workType "book-chapter" @default.