Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891524928> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2891524928 abstract "Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new classification task. While this reprogramming approach works for neural networks with a continuous input space such as that of images, it is not directly applicable to neural networks trained for tasks such as text classification, where the input space is discrete. Repurposing such classification networks would require the attacker to learn an adversarial program that maps inputs from one discrete space to the other. In this work, we introduce a context-based vocabulary remapping model to reprogram neural networks trained on a specific sequence classification task, for a new sequence classification task desired by the adversary. We propose training procedures for this adversarial program in both white-box and black-box settings. We demonstrate the application of our model by adversarially repurposing various text-classification models including LSTM, bi-directional LSTM and CNN for alternate classification tasks." @default.
- W2891524928 created "2018-09-27" @default.
- W2891524928 creator A5015232966 @default.
- W2891524928 creator A5030710635 @default.
- W2891524928 creator A5042278809 @default.
- W2891524928 creator A5063273639 @default.
- W2891524928 date "2018-09-06" @default.
- W2891524928 modified "2023-09-27" @default.
- W2891524928 title "Adversarial Reprogramming of Sequence Classification Neural Networks." @default.
- W2891524928 hasPublicationYear "2018" @default.
- W2891524928 type Work @default.
- W2891524928 sameAs 2891524928 @default.
- W2891524928 citedByCount "1" @default.
- W2891524928 countsByYear W28915249282020 @default.
- W2891524928 crossrefType "posted-content" @default.
- W2891524928 hasAuthorship W2891524928A5015232966 @default.
- W2891524928 hasAuthorship W2891524928A5030710635 @default.
- W2891524928 hasAuthorship W2891524928A5042278809 @default.
- W2891524928 hasAuthorship W2891524928A5063273639 @default.
- W2891524928 hasConcept C119857082 @default.
- W2891524928 hasConcept C151730666 @default.
- W2891524928 hasConcept C154945302 @default.
- W2891524928 hasConcept C162324750 @default.
- W2891524928 hasConcept C187736073 @default.
- W2891524928 hasConcept C18903297 @default.
- W2891524928 hasConcept C2778112365 @default.
- W2891524928 hasConcept C2779343474 @default.
- W2891524928 hasConcept C2780451532 @default.
- W2891524928 hasConcept C37736160 @default.
- W2891524928 hasConcept C38652104 @default.
- W2891524928 hasConcept C41008148 @default.
- W2891524928 hasConcept C41065033 @default.
- W2891524928 hasConcept C50644808 @default.
- W2891524928 hasConcept C519536355 @default.
- W2891524928 hasConcept C54355233 @default.
- W2891524928 hasConcept C86803240 @default.
- W2891524928 hasConceptScore W2891524928C119857082 @default.
- W2891524928 hasConceptScore W2891524928C151730666 @default.
- W2891524928 hasConceptScore W2891524928C154945302 @default.
- W2891524928 hasConceptScore W2891524928C162324750 @default.
- W2891524928 hasConceptScore W2891524928C187736073 @default.
- W2891524928 hasConceptScore W2891524928C18903297 @default.
- W2891524928 hasConceptScore W2891524928C2778112365 @default.
- W2891524928 hasConceptScore W2891524928C2779343474 @default.
- W2891524928 hasConceptScore W2891524928C2780451532 @default.
- W2891524928 hasConceptScore W2891524928C37736160 @default.
- W2891524928 hasConceptScore W2891524928C38652104 @default.
- W2891524928 hasConceptScore W2891524928C41008148 @default.
- W2891524928 hasConceptScore W2891524928C41065033 @default.
- W2891524928 hasConceptScore W2891524928C50644808 @default.
- W2891524928 hasConceptScore W2891524928C519536355 @default.
- W2891524928 hasConceptScore W2891524928C54355233 @default.
- W2891524928 hasConceptScore W2891524928C86803240 @default.
- W2891524928 hasLocation W28915249281 @default.
- W2891524928 hasOpenAccess W2891524928 @default.
- W2891524928 hasPrimaryLocation W28915249281 @default.
- W2891524928 hasRelatedWork W2180612164 @default.
- W2891524928 hasRelatedWork W2550814094 @default.
- W2891524928 hasRelatedWork W2599207826 @default.
- W2891524928 hasRelatedWork W2753626192 @default.
- W2891524928 hasRelatedWork W2781800156 @default.
- W2891524928 hasRelatedWork W2783819585 @default.
- W2891524928 hasRelatedWork W2799012717 @default.
- W2891524928 hasRelatedWork W2806278221 @default.
- W2891524928 hasRelatedWork W2807621872 @default.
- W2891524928 hasRelatedWork W2903917280 @default.
- W2891524928 hasRelatedWork W2963294943 @default.
- W2891524928 hasRelatedWork W2969026700 @default.
- W2891524928 hasRelatedWork W2986674980 @default.
- W2891524928 hasRelatedWork W3040148743 @default.
- W2891524928 hasRelatedWork W3091438609 @default.
- W2891524928 hasRelatedWork W3096804204 @default.
- W2891524928 hasRelatedWork W3109321589 @default.
- W2891524928 hasRelatedWork W3113929890 @default.
- W2891524928 hasRelatedWork W3157177672 @default.
- W2891524928 hasRelatedWork W3201909459 @default.
- W2891524928 isParatext "false" @default.
- W2891524928 isRetracted "false" @default.
- W2891524928 magId "2891524928" @default.
- W2891524928 workType "article" @default.