Matches in SemOpenAlex for { <https://semopenalex.org/work/W2935349488> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2935349488 abstract "Deep Learning (DL) models have created a paradigm shift in our ability to comprehend raw data in various important fields, ranging from intelligence warfare and healthcare to autonomous transportation and automated manufacturing. A practical concern, in the rush to adopt DL models as a service, is protecting the models against Intellectual Property (IP) infringement. DL models are commonly built by allocating substantial computational resources that process vast amounts of proprietary training data. The resulting models are therefore considered to be an IP of the model builder and need to be protected to preserve the owner's competitive advantage. We propose DeepSigns, the first end-to-end IP protection framework that enables developers to systematically insert digital watermarks in the target DL model before distributing the model. DeepSigns is encapsulated as a high-level wrapper that can be leveraged within common deep learning frameworks including TensorFlow and PyTorch. The libraries in DeepSigns work by dynamically learning the Probability Density Function (pdf) of activation maps obtained in different layers of a DL model. DeepSigns uses the low probabilistic regions within the model to gradually embed the owner's signature (watermark) during DL training while minimally affecting the overall accuracy and training overhead. DeepSigns can demonstrably withstand various removal and transformation attacks, including model pruning, model fine-tuning, and watermark overwriting. We evaluate DeepSigns performance on a wide variety of DL architectures including wide residual convolution neural networks, multi-layer perceptrons, and long short-term memory models. Our extensive evaluations corroborate DeepSigns' effectiveness and applicability. We further provide a highly-optimized accompanying API to facilitate training watermarked neural networks with a training overhead as low as 2.2%." @default.
- W2935349488 created "2019-04-11" @default.
- W2935349488 creator A5007747700 @default.
- W2935349488 creator A5019931011 @default.
- W2935349488 creator A5035073741 @default.
- W2935349488 date "2019-04-04" @default.
- W2935349488 modified "2023-10-12" @default.
- W2935349488 title "DeepSigns" @default.
- W2935349488 cites W1599779438 @default.
- W2935349488 cites W1934184906 @default.
- W2935349488 cites W2108598243 @default.
- W2935349488 cites W2116467012 @default.
- W2935349488 cites W2294710185 @default.
- W2935349488 cites W2346062110 @default.
- W2935349488 cites W2488255893 @default.
- W2935349488 cites W2579318729 @default.
- W2935349488 cites W2603766943 @default.
- W2935349488 cites W2625592091 @default.
- W2935349488 cites W2798956872 @default.
- W2935349488 cites W2888062646 @default.
- W2935349488 cites W2919115771 @default.
- W2935349488 cites W2964137095 @default.
- W2935349488 cites W3105676597 @default.
- W2935349488 cites W4205947740 @default.
- W2935349488 doi "https://doi.org/10.1145/3297858.3304051" @default.
- W2935349488 hasPublicationYear "2019" @default.
- W2935349488 type Work @default.
- W2935349488 sameAs 2935349488 @default.
- W2935349488 citedByCount "85" @default.
- W2935349488 countsByYear W29353494882019 @default.
- W2935349488 countsByYear W29353494882020 @default.
- W2935349488 countsByYear W29353494882021 @default.
- W2935349488 countsByYear W29353494882022 @default.
- W2935349488 countsByYear W29353494882023 @default.
- W2935349488 crossrefType "proceedings-article" @default.
- W2935349488 hasAuthorship W2935349488A5007747700 @default.
- W2935349488 hasAuthorship W2935349488A5019931011 @default.
- W2935349488 hasAuthorship W2935349488A5035073741 @default.
- W2935349488 hasBestOaLocation W29353494881 @default.
- W2935349488 hasConcept C104317684 @default.
- W2935349488 hasConcept C108583219 @default.
- W2935349488 hasConcept C111919701 @default.
- W2935349488 hasConcept C119857082 @default.
- W2935349488 hasConcept C138236772 @default.
- W2935349488 hasConcept C154945302 @default.
- W2935349488 hasConcept C185592680 @default.
- W2935349488 hasConcept C204241405 @default.
- W2935349488 hasConcept C2779960059 @default.
- W2935349488 hasConcept C41008148 @default.
- W2935349488 hasConcept C49937458 @default.
- W2935349488 hasConcept C55493867 @default.
- W2935349488 hasConcept C79974875 @default.
- W2935349488 hasConcept C81363708 @default.
- W2935349488 hasConcept C98045186 @default.
- W2935349488 hasConceptScore W2935349488C104317684 @default.
- W2935349488 hasConceptScore W2935349488C108583219 @default.
- W2935349488 hasConceptScore W2935349488C111919701 @default.
- W2935349488 hasConceptScore W2935349488C119857082 @default.
- W2935349488 hasConceptScore W2935349488C138236772 @default.
- W2935349488 hasConceptScore W2935349488C154945302 @default.
- W2935349488 hasConceptScore W2935349488C185592680 @default.
- W2935349488 hasConceptScore W2935349488C204241405 @default.
- W2935349488 hasConceptScore W2935349488C2779960059 @default.
- W2935349488 hasConceptScore W2935349488C41008148 @default.
- W2935349488 hasConceptScore W2935349488C49937458 @default.
- W2935349488 hasConceptScore W2935349488C55493867 @default.
- W2935349488 hasConceptScore W2935349488C79974875 @default.
- W2935349488 hasConceptScore W2935349488C81363708 @default.
- W2935349488 hasConceptScore W2935349488C98045186 @default.
- W2935349488 hasLocation W29353494881 @default.
- W2935349488 hasOpenAccess W2935349488 @default.
- W2935349488 hasPrimaryLocation W29353494881 @default.
- W2935349488 hasRelatedWork W2572334665 @default.
- W2935349488 hasRelatedWork W2731899572 @default.
- W2935349488 hasRelatedWork W2920938200 @default.
- W2935349488 hasRelatedWork W3021430260 @default.
- W2935349488 hasRelatedWork W3159901390 @default.
- W2935349488 hasRelatedWork W3164822677 @default.
- W2935349488 hasRelatedWork W3196211586 @default.
- W2935349488 hasRelatedWork W3215138031 @default.
- W2935349488 hasRelatedWork W4220755519 @default.
- W2935349488 hasRelatedWork W4226246648 @default.
- W2935349488 isParatext "false" @default.
- W2935349488 isRetracted "false" @default.
- W2935349488 magId "2935349488" @default.
- W2935349488 workType "article" @default.