Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312337675> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4312337675 endingPage "104" @default.
- W4312337675 startingPage "93" @default.
- W4312337675 abstract "In many scenarios, people have a demand for deploying the artificial intelligence applications on the edge device of IoT. For some special applications, these embedded devices are always required real-time reponse; hence, it is necessary to process machine learning algorithms on microprocessors. However, these devices may be subjected to side-channel attacks (SCA). During the execution, these devices will generate the leakage information can be captured to get the secret data. In this work, we investigate how to reverse engineer the weights of a convolutional neural network (CNN) which is deployed on ARM Cortex-M3 using Chosen Pixel Horizontal Power Analysis (CP-HPA). We conduct the experiment on ELMO emulating leaks for the ARM Cortex-M3. ARM Cortex-M3 microprocessors are often used to deploy CNNs. Here, we show that it is possible to recover the weights of a CNN using CP-HPA assuming that the adversary only has the knowledge of the architectures. We increase the accuracy of our attack through setting up chosen input pixel to correlate the selected multiplication. We are able to successfully recover the weights of a CMSIS-NN implementation CNN, and accuracy of our attack is 84.625%." @default.
- W4312337675 created "2023-01-04" @default.
- W4312337675 creator A5019829754 @default.
- W4312337675 creator A5025551938 @default.
- W4312337675 creator A5044757881 @default.
- W4312337675 creator A5051178495 @default.
- W4312337675 creator A5084539496 @default.
- W4312337675 creator A5091161457 @default.
- W4312337675 date "2022-01-01" @default.
- W4312337675 modified "2023-10-16" @default.
- W4312337675 title "Recovering the Weights of Convolutional Neural Network via Chosen Pixel Horizontal Power Analysis" @default.
- W4312337675 cites W1515200869 @default.
- W4312337675 cites W1562542037 @default.
- W4312337675 cites W1565369953 @default.
- W4312337675 cites W1885172175 @default.
- W4312337675 cites W1977655452 @default.
- W4312337675 cites W2075043695 @default.
- W4312337675 cites W2127059139 @default.
- W4312337675 cites W2154909745 @default.
- W4312337675 cites W2523737168 @default.
- W4312337675 cites W2914572864 @default.
- W4312337675 cites W2984453562 @default.
- W4312337675 cites W3150590753 @default.
- W4312337675 cites W4246001895 @default.
- W4312337675 doi "https://doi.org/10.1007/978-3-031-19214-2_8" @default.
- W4312337675 hasPublicationYear "2022" @default.
- W4312337675 type Work @default.
- W4312337675 citedByCount "0" @default.
- W4312337675 crossrefType "book-chapter" @default.
- W4312337675 hasAuthorship W4312337675A5019829754 @default.
- W4312337675 hasAuthorship W4312337675A5025551938 @default.
- W4312337675 hasAuthorship W4312337675A5044757881 @default.
- W4312337675 hasAuthorship W4312337675A5051178495 @default.
- W4312337675 hasAuthorship W4312337675A5084539496 @default.
- W4312337675 hasAuthorship W4312337675A5091161457 @default.
- W4312337675 hasConcept C111919701 @default.
- W4312337675 hasConcept C11413529 @default.
- W4312337675 hasConcept C121332964 @default.
- W4312337675 hasConcept C138236772 @default.
- W4312337675 hasConcept C149635348 @default.
- W4312337675 hasConcept C154945302 @default.
- W4312337675 hasConcept C160633673 @default.
- W4312337675 hasConcept C162307627 @default.
- W4312337675 hasConcept C178489894 @default.
- W4312337675 hasConcept C24890656 @default.
- W4312337675 hasConcept C26771161 @default.
- W4312337675 hasConcept C2780595030 @default.
- W4312337675 hasConcept C41008148 @default.
- W4312337675 hasConcept C49289754 @default.
- W4312337675 hasConcept C50644808 @default.
- W4312337675 hasConcept C71743495 @default.
- W4312337675 hasConcept C79974875 @default.
- W4312337675 hasConcept C81363708 @default.
- W4312337675 hasConcept C9390403 @default.
- W4312337675 hasConcept C98045186 @default.
- W4312337675 hasConceptScore W4312337675C111919701 @default.
- W4312337675 hasConceptScore W4312337675C11413529 @default.
- W4312337675 hasConceptScore W4312337675C121332964 @default.
- W4312337675 hasConceptScore W4312337675C138236772 @default.
- W4312337675 hasConceptScore W4312337675C149635348 @default.
- W4312337675 hasConceptScore W4312337675C154945302 @default.
- W4312337675 hasConceptScore W4312337675C160633673 @default.
- W4312337675 hasConceptScore W4312337675C162307627 @default.
- W4312337675 hasConceptScore W4312337675C178489894 @default.
- W4312337675 hasConceptScore W4312337675C24890656 @default.
- W4312337675 hasConceptScore W4312337675C26771161 @default.
- W4312337675 hasConceptScore W4312337675C2780595030 @default.
- W4312337675 hasConceptScore W4312337675C41008148 @default.
- W4312337675 hasConceptScore W4312337675C49289754 @default.
- W4312337675 hasConceptScore W4312337675C50644808 @default.
- W4312337675 hasConceptScore W4312337675C71743495 @default.
- W4312337675 hasConceptScore W4312337675C79974875 @default.
- W4312337675 hasConceptScore W4312337675C81363708 @default.
- W4312337675 hasConceptScore W4312337675C9390403 @default.
- W4312337675 hasConceptScore W4312337675C98045186 @default.
- W4312337675 hasLocation W43123376751 @default.
- W4312337675 hasOpenAccess W4312337675 @default.
- W4312337675 hasPrimaryLocation W43123376751 @default.
- W4312337675 hasRelatedWork W2276492996 @default.
- W4312337675 hasRelatedWork W2417559148 @default.
- W4312337675 hasRelatedWork W265063938 @default.
- W4312337675 hasRelatedWork W2794898833 @default.
- W4312337675 hasRelatedWork W2797314256 @default.
- W4312337675 hasRelatedWork W2950536398 @default.
- W4312337675 hasRelatedWork W3034754805 @default.
- W4312337675 hasRelatedWork W4200364167 @default.
- W4312337675 hasRelatedWork W4376106090 @default.
- W4312337675 hasRelatedWork W2188111145 @default.
- W4312337675 isParatext "false" @default.
- W4312337675 isRetracted "false" @default.
- W4312337675 workType "book-chapter" @default.