Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317382419> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4317382419 abstract "This paper proposes a method to attack embedding-based text classifiers, namely GenEmC, to reduce the high computational cost of rule-based replacement. GenEmC includes three main steps including data preparation, embedding decoder training, and generator training. The embedding decoder is learned to convert embedding vectors to texts. The generator is trained by a two-term loss to generate adversarial embedding vectors from original texts. After three steps, the combination of two trained models could generate adversarial texts instantly. To demonstrate the effectiveness of GenEmC, the experiments are conducted on the IMDB dataset. The target classifiers are well-trained GRU, LSTM, and Bert. GenEmC is compared with two well-known rule-based replacement methods known as PWWS and TextBugger. The experiments have demonstrated that for 1,000 texts in test set, while the computational cost of GenEmC is an average of about 6 minutes, the others require at least 10 hours. Besides, the average success rate and semantic-preserving output score of GenEmC is moderately higher than those of PWWS and TextBugger." @default.
- W4317382419 created "2023-01-19" @default.
- W4317382419 creator A5020815082 @default.
- W4317382419 creator A5027582055 @default.
- W4317382419 creator A5077353707 @default.
- W4317382419 creator A5079840241 @default.
- W4317382419 date "2022-12-20" @default.
- W4317382419 modified "2023-10-18" @default.
- W4317382419 title "A Generator-based Method for Attacking Embedding-based Text Classifiers" @default.
- W4317382419 cites W1832693441 @default.
- W4317382419 cites W2064675550 @default.
- W4317382419 cites W2250539671 @default.
- W4317382419 cites W2609368435 @default.
- W4317382419 cites W2949128310 @default.
- W4317382419 cites W2963859254 @default.
- W4317382419 cites W2963913218 @default.
- W4317382419 cites W2964199361 @default.
- W4317382419 cites W3007157104 @default.
- W4317382419 cites W3015001695 @default.
- W4317382419 cites W3092288641 @default.
- W4317382419 cites W3101118235 @default.
- W4317382419 cites W3105604018 @default.
- W4317382419 doi "https://doi.org/10.1109/rivf55975.2022.10013912" @default.
- W4317382419 hasPublicationYear "2022" @default.
- W4317382419 type Work @default.
- W4317382419 citedByCount "0" @default.
- W4317382419 crossrefType "proceedings-article" @default.
- W4317382419 hasAuthorship W4317382419A5020815082 @default.
- W4317382419 hasAuthorship W4317382419A5027582055 @default.
- W4317382419 hasAuthorship W4317382419A5077353707 @default.
- W4317382419 hasAuthorship W4317382419A5079840241 @default.
- W4317382419 hasConcept C119857082 @default.
- W4317382419 hasConcept C121332964 @default.
- W4317382419 hasConcept C153180895 @default.
- W4317382419 hasConcept C154945302 @default.
- W4317382419 hasConcept C163258240 @default.
- W4317382419 hasConcept C177264268 @default.
- W4317382419 hasConcept C199360897 @default.
- W4317382419 hasConcept C2780992000 @default.
- W4317382419 hasConcept C37736160 @default.
- W4317382419 hasConcept C41008148 @default.
- W4317382419 hasConcept C41608201 @default.
- W4317382419 hasConcept C51632099 @default.
- W4317382419 hasConcept C62520636 @default.
- W4317382419 hasConceptScore W4317382419C119857082 @default.
- W4317382419 hasConceptScore W4317382419C121332964 @default.
- W4317382419 hasConceptScore W4317382419C153180895 @default.
- W4317382419 hasConceptScore W4317382419C154945302 @default.
- W4317382419 hasConceptScore W4317382419C163258240 @default.
- W4317382419 hasConceptScore W4317382419C177264268 @default.
- W4317382419 hasConceptScore W4317382419C199360897 @default.
- W4317382419 hasConceptScore W4317382419C2780992000 @default.
- W4317382419 hasConceptScore W4317382419C37736160 @default.
- W4317382419 hasConceptScore W4317382419C41008148 @default.
- W4317382419 hasConceptScore W4317382419C41608201 @default.
- W4317382419 hasConceptScore W4317382419C51632099 @default.
- W4317382419 hasConceptScore W4317382419C62520636 @default.
- W4317382419 hasLocation W43173824191 @default.
- W4317382419 hasOpenAccess W4317382419 @default.
- W4317382419 hasPrimaryLocation W43173824191 @default.
- W4317382419 hasRelatedWork W3015366916 @default.
- W4317382419 hasRelatedWork W3025331699 @default.
- W4317382419 hasRelatedWork W3035729345 @default.
- W4317382419 hasRelatedWork W3046843850 @default.
- W4317382419 hasRelatedWork W3154304377 @default.
- W4317382419 hasRelatedWork W3182186294 @default.
- W4317382419 hasRelatedWork W3201070945 @default.
- W4317382419 hasRelatedWork W3201905201 @default.
- W4317382419 hasRelatedWork W4312741812 @default.
- W4317382419 hasRelatedWork W4386716251 @default.
- W4317382419 isParatext "false" @default.
- W4317382419 isRetracted "false" @default.
- W4317382419 workType "article" @default.