Matches in SemOpenAlex for { <https://semopenalex.org/work/W3118164462> ?p ?o ?g. }
- W3118164462 abstract "Differential Power Analysis (DPA) has been an active area of research for the past two decades to study the attacks for extracting secret information from cryptographic implementations through power measurements and their defenses. The research on power side-channels have so far predominantly focused on analyzing implementations of ciphers such as AES, DES, RSA, and recently post-quantum cryptography primitives (e.g., lattices). Meanwhile, machine-learning applications are becoming ubiquitous with several scenarios where the Machine Learning Models are Intellectual Properties requiring confidentiality. Expanding side-channel analysis to Machine Learning Model extraction, however, is largely unexplored. This paper expands the DPA framework to neural-network classifiers. First, it shows DPA attacks during inference to extract the secret model parameters such as weights and biases of a neural network. Second, it proposes the first countermeasures against these attacks by augmenting masking. The resulting design uses novel masked components such as masked adder trees for fully-connected layers and masked Rectifier Linear Units for activation functions. On a SAKURA-X FPGA board, experiments show that the first-order DPA attacks on the unprotected implementation can succeed with only 200 traces and our protection respectively increases the latency and area-cost by 2.8× and 2.3×." @default.
- W3118164462 created "2021-01-05" @default.
- W3118164462 creator A5008761074 @default.
- W3118164462 creator A5062027964 @default.
- W3118164462 creator A5085883266 @default.
- W3118164462 date "2020-12-07" @default.
- W3118164462 modified "2023-09-24" @default.
- W3118164462 title "MaskedNet: The First Hardware Inference Engine Aiming Power Side-Channel Protection" @default.
- W3118164462 cites W1503689022 @default.
- W3118164462 cites W1564536482 @default.
- W3118164462 cites W1873852107 @default.
- W3118164462 cites W1992291252 @default.
- W3118164462 cites W2005006301 @default.
- W3118164462 cites W2021705882 @default.
- W3118164462 cites W2037844954 @default.
- W3118164462 cites W2053832511 @default.
- W3118164462 cites W2127059139 @default.
- W3118164462 cites W2155938490 @default.
- W3118164462 cites W2180612164 @default.
- W3118164462 cites W2293214346 @default.
- W3118164462 cites W2293768274 @default.
- W3118164462 cites W2296452361 @default.
- W3118164462 cites W2300242332 @default.
- W3118164462 cites W2535690855 @default.
- W3118164462 cites W2535955463 @default.
- W3118164462 cites W2556867355 @default.
- W3118164462 cites W2591922920 @default.
- W3118164462 cites W2603766943 @default.
- W3118164462 cites W2724189024 @default.
- W3118164462 cites W2739889860 @default.
- W3118164462 cites W2794898833 @default.
- W3118164462 cites W2798781612 @default.
- W3118164462 cites W2891810898 @default.
- W3118164462 cites W2892344663 @default.
- W3118164462 cites W2929412763 @default.
- W3118164462 cites W2934725803 @default.
- W3118164462 cites W2949105280 @default.
- W3118164462 cites W2963844355 @default.
- W3118164462 cites W3102169921 @default.
- W3118164462 cites W3105997554 @default.
- W3118164462 cites W4231098049 @default.
- W3118164462 cites W4238612353 @default.
- W3118164462 cites W4238821589 @default.
- W3118164462 cites W4246001895 @default.
- W3118164462 cites W4254071860 @default.
- W3118164462 cites W4289146347 @default.
- W3118164462 doi "https://doi.org/10.1109/host45689.2020.9300276" @default.
- W3118164462 hasPublicationYear "2020" @default.
- W3118164462 type Work @default.
- W3118164462 sameAs 3118164462 @default.
- W3118164462 citedByCount "32" @default.
- W3118164462 countsByYear W31181644622021 @default.
- W3118164462 countsByYear W31181644622022 @default.
- W3118164462 countsByYear W31181644622023 @default.
- W3118164462 crossrefType "proceedings-article" @default.
- W3118164462 hasAuthorship W3118164462A5008761074 @default.
- W3118164462 hasAuthorship W3118164462A5062027964 @default.
- W3118164462 hasAuthorship W3118164462A5085883266 @default.
- W3118164462 hasBestOaLocation W31181644622 @default.
- W3118164462 hasConcept C113775141 @default.
- W3118164462 hasConcept C142362112 @default.
- W3118164462 hasConcept C149635348 @default.
- W3118164462 hasConcept C153349607 @default.
- W3118164462 hasConcept C154945302 @default.
- W3118164462 hasConcept C164620267 @default.
- W3118164462 hasConcept C178489894 @default.
- W3118164462 hasConcept C2777402240 @default.
- W3118164462 hasConcept C38652104 @default.
- W3118164462 hasConcept C41008148 @default.
- W3118164462 hasConcept C42935608 @default.
- W3118164462 hasConcept C49289754 @default.
- W3118164462 hasConcept C50644808 @default.
- W3118164462 hasConcept C71743495 @default.
- W3118164462 hasConcept C76155785 @default.
- W3118164462 hasConcept C82876162 @default.
- W3118164462 hasConcept C9390403 @default.
- W3118164462 hasConceptScore W3118164462C113775141 @default.
- W3118164462 hasConceptScore W3118164462C142362112 @default.
- W3118164462 hasConceptScore W3118164462C149635348 @default.
- W3118164462 hasConceptScore W3118164462C153349607 @default.
- W3118164462 hasConceptScore W3118164462C154945302 @default.
- W3118164462 hasConceptScore W3118164462C164620267 @default.
- W3118164462 hasConceptScore W3118164462C178489894 @default.
- W3118164462 hasConceptScore W3118164462C2777402240 @default.
- W3118164462 hasConceptScore W3118164462C38652104 @default.
- W3118164462 hasConceptScore W3118164462C41008148 @default.
- W3118164462 hasConceptScore W3118164462C42935608 @default.
- W3118164462 hasConceptScore W3118164462C49289754 @default.
- W3118164462 hasConceptScore W3118164462C50644808 @default.
- W3118164462 hasConceptScore W3118164462C71743495 @default.
- W3118164462 hasConceptScore W3118164462C76155785 @default.
- W3118164462 hasConceptScore W3118164462C82876162 @default.
- W3118164462 hasConceptScore W3118164462C9390403 @default.
- W3118164462 hasLocation W31181644621 @default.
- W3118164462 hasLocation W31181644622 @default.
- W3118164462 hasOpenAccess W3118164462 @default.
- W3118164462 hasPrimaryLocation W31181644621 @default.
- W3118164462 hasRelatedWork W1515909117 @default.
- W3118164462 hasRelatedWork W2012930062 @default.
- W3118164462 hasRelatedWork W2113243482 @default.