Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304192617> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4304192617 abstract "Deep neural networks (DNNs) are utilized in numerous image processing, object detection, and video analysis tasks and need to be implemented using hardware accelerators to achieve practical speed. Logic locking is one of the most popular methods for preventing chip counterfeiting. Nevertheless, existing logic-locking schemes need to sacrifice the number of input patterns leading to wrong output under incorrect keys to resist the powerful satisfiability (SAT)-attack. Furthermore, DNN model inference is fault-tolerant. Hence, using a wrong key for those SAT-resistant logic-locking schemes may not affect the accuracy of DNNs. This makes the previous SAT-resistant logic-locking scheme ineffective on protecting DNN accelerators. Besides, to prevent DNN models from being illegally used, the models need to be obfuscated by the designers before they are provided to end-users. Previous obfuscation methods either require long time to retrain the model or leak information about the model. This paper proposes a joint protection scheme for DNN hardware accelerators and models. The DNN accelerator is modified using a hardware key (Hkey) and a model key (Mkey). Different from previous logic locking, the Hkey, which is used to protect the accelerator, does not affect the output when it is wrong. As a result, the SAT attack can be effectively resisted. On the other hand, a wrong Hkey leads to substantial increase in memory accesses, inference time, and energy consumption and makes the accelerator unusable. A correct Mkey can recover the DNN model that is obfuscated by the proposed method. Compared to previous model obfuscation schemes, our proposed method avoids model retraining and does not leak model information." @default.
- W4304192617 created "2022-10-11" @default.
- W4304192617 creator A5044742215 @default.
- W4304192617 creator A5063673084 @default.
- W4304192617 date "2022-10-06" @default.
- W4304192617 modified "2023-10-07" @default.
- W4304192617 title "Joint Protection Scheme for Deep Neural Network Hardware Accelerators and Models" @default.
- W4304192617 doi "https://doi.org/10.48550/arxiv.2210.03249" @default.
- W4304192617 hasPublicationYear "2022" @default.
- W4304192617 type Work @default.
- W4304192617 citedByCount "0" @default.
- W4304192617 crossrefType "posted-content" @default.
- W4304192617 hasAuthorship W4304192617A5044742215 @default.
- W4304192617 hasAuthorship W4304192617A5063673084 @default.
- W4304192617 hasBestOaLocation W43041926171 @default.
- W4304192617 hasConcept C113775141 @default.
- W4304192617 hasConcept C127413603 @default.
- W4304192617 hasConcept C134306372 @default.
- W4304192617 hasConcept C149635348 @default.
- W4304192617 hasConcept C154945302 @default.
- W4304192617 hasConcept C170154142 @default.
- W4304192617 hasConcept C18555067 @default.
- W4304192617 hasConcept C26517878 @default.
- W4304192617 hasConcept C2776214188 @default.
- W4304192617 hasConcept C33923547 @default.
- W4304192617 hasConcept C38652104 @default.
- W4304192617 hasConcept C40305131 @default.
- W4304192617 hasConcept C41008148 @default.
- W4304192617 hasConcept C50644808 @default.
- W4304192617 hasConcept C77618280 @default.
- W4304192617 hasConcept C9390403 @default.
- W4304192617 hasConceptScore W4304192617C113775141 @default.
- W4304192617 hasConceptScore W4304192617C127413603 @default.
- W4304192617 hasConceptScore W4304192617C134306372 @default.
- W4304192617 hasConceptScore W4304192617C149635348 @default.
- W4304192617 hasConceptScore W4304192617C154945302 @default.
- W4304192617 hasConceptScore W4304192617C170154142 @default.
- W4304192617 hasConceptScore W4304192617C18555067 @default.
- W4304192617 hasConceptScore W4304192617C26517878 @default.
- W4304192617 hasConceptScore W4304192617C2776214188 @default.
- W4304192617 hasConceptScore W4304192617C33923547 @default.
- W4304192617 hasConceptScore W4304192617C38652104 @default.
- W4304192617 hasConceptScore W4304192617C40305131 @default.
- W4304192617 hasConceptScore W4304192617C41008148 @default.
- W4304192617 hasConceptScore W4304192617C50644808 @default.
- W4304192617 hasConceptScore W4304192617C77618280 @default.
- W4304192617 hasConceptScore W4304192617C9390403 @default.
- W4304192617 hasLocation W43041926171 @default.
- W4304192617 hasOpenAccess W4304192617 @default.
- W4304192617 hasPrimaryLocation W43041926171 @default.
- W4304192617 hasRelatedWork W2351197619 @default.
- W4304192617 hasRelatedWork W2361565340 @default.
- W4304192617 hasRelatedWork W2365477072 @default.
- W4304192617 hasRelatedWork W2372177958 @default.
- W4304192617 hasRelatedWork W2381642967 @default.
- W4304192617 hasRelatedWork W2383665363 @default.
- W4304192617 hasRelatedWork W2387725353 @default.
- W4304192617 hasRelatedWork W2393670011 @default.
- W4304192617 hasRelatedWork W4205177888 @default.
- W4304192617 hasRelatedWork W4286981775 @default.
- W4304192617 isParatext "false" @default.
- W4304192617 isRetracted "false" @default.
- W4304192617 workType "article" @default.