Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298575286> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4298575286 abstract "Today’s intelligent services are built on well-trained deep neural network (DNN) models, which usually require large private datasets along with a high cost for model training. It consequently makes the model providers cherish the pre-trained DNN models and only distribute them to authorized users. However, malicious users can steal these valuable models for abuse, illegal copy and redistribution. Attackers can also extract private features from even authorized models to leak partial training datasets. They both violate privacy. Existing techniques from secure community attempt to avoid parameter leakage during model authorization but yet cannot solve privacy issues sufficiently. In this paper, we propose a privacy-preserving model authorization approach, AgAuth, to resist the aforementioned privacy threats. We devise a novel scheme called Information-Agnostic Conversion (IAC) for forwarding procedure to eliminate residual features in model parameters. Based on it, we then propose Inference-on-Ciphertext (CiFer) mechanism for DNN reasoning, which includes three stages in each forwarding. The Encrypt phase first converts the proprietary model parameters to demonstrate uniform distribution. The Forward stage per-forms forwarding function without decryption at authorized side. Specifically, this stage just computes over ciphertext. The Decrypt phase finally recovers the information-agnostic outputs to informative output tensor for real-world services. In addition, we implement a prototype and conduct extensive experiments to evaluate its performance. The qualitative and quantitative results demonstrate that our solution AgAuth is privacy-preserving to defend against model theft and feature leakage, without accuracy loss or notable performance decrease." @default.
- W4298575286 created "2022-10-02" @default.
- W4298575286 creator A5015419107 @default.
- W4298575286 creator A5025635683 @default.
- W4298575286 creator A5052528809 @default.
- W4298575286 creator A5069049205 @default.
- W4298575286 date "2022-05-16" @default.
- W4298575286 modified "2023-09-25" @default.
- W4298575286 title "Privacy-Preserving DNN Model Authorization against Model Theft and Feature Leakage" @default.
- W4298575286 doi "https://doi.org/10.1109/icc45855.2022.9839218" @default.
- W4298575286 hasPublicationYear "2022" @default.
- W4298575286 type Work @default.
- W4298575286 citedByCount "0" @default.
- W4298575286 crossrefType "proceedings-article" @default.
- W4298575286 hasAuthorship W4298575286A5015419107 @default.
- W4298575286 hasAuthorship W4298575286A5025635683 @default.
- W4298575286 hasAuthorship W4298575286A5052528809 @default.
- W4298575286 hasAuthorship W4298575286A5069049205 @default.
- W4298575286 hasConcept C108759981 @default.
- W4298575286 hasConcept C124101348 @default.
- W4298575286 hasConcept C148730421 @default.
- W4298575286 hasConcept C154945302 @default.
- W4298575286 hasConcept C2776214188 @default.
- W4298575286 hasConcept C2779201187 @default.
- W4298575286 hasConcept C38652104 @default.
- W4298575286 hasConcept C41008148 @default.
- W4298575286 hasConcept C50644808 @default.
- W4298575286 hasConcept C93974786 @default.
- W4298575286 hasConceptScore W4298575286C108759981 @default.
- W4298575286 hasConceptScore W4298575286C124101348 @default.
- W4298575286 hasConceptScore W4298575286C148730421 @default.
- W4298575286 hasConceptScore W4298575286C154945302 @default.
- W4298575286 hasConceptScore W4298575286C2776214188 @default.
- W4298575286 hasConceptScore W4298575286C2779201187 @default.
- W4298575286 hasConceptScore W4298575286C38652104 @default.
- W4298575286 hasConceptScore W4298575286C41008148 @default.
- W4298575286 hasConceptScore W4298575286C50644808 @default.
- W4298575286 hasConceptScore W4298575286C93974786 @default.
- W4298575286 hasFunder F4320321001 @default.
- W4298575286 hasFunder F4320322392 @default.
- W4298575286 hasFunder F4320322843 @default.
- W4298575286 hasFunder F4320337504 @default.
- W4298575286 hasLocation W42985752861 @default.
- W4298575286 hasOpenAccess W4298575286 @default.
- W4298575286 hasPrimaryLocation W42985752861 @default.
- W4298575286 hasRelatedWork W1484404656 @default.
- W4298575286 hasRelatedWork W2060783077 @default.
- W4298575286 hasRelatedWork W2322106752 @default.
- W4298575286 hasRelatedWork W2493534553 @default.
- W4298575286 hasRelatedWork W2772745781 @default.
- W4298575286 hasRelatedWork W2902609404 @default.
- W4298575286 hasRelatedWork W2906296395 @default.
- W4298575286 hasRelatedWork W2985562172 @default.
- W4298575286 hasRelatedWork W2994322320 @default.
- W4298575286 hasRelatedWork W2531168132 @default.
- W4298575286 isParatext "false" @default.
- W4298575286 isRetracted "false" @default.
- W4298575286 workType "article" @default.