Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211197554> ?p ?o ?g. }
- W3211197554 abstract "Adversarial example generation has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to improve the robustness of DNN models. Due to the extensiveness and high liquidity of natural language over the social networks, various natural language based adversarial attack algorithms have been proposed in the literature. These algorithms generate adversarial text examples with high semantic quality. However, the generated adversarial text examples may be maliciously or illegally used. In order to tackle with this problem, we present a general framework for generating watermarked adversarial text examples. For each word in a given text, a set of candidate words are determined to ensure that all the words in the set can be used to either carry secret bits or facilitate the construction of adversarial example. By applying a word-level adversarial text generation algorithm, the watermarked adversarial text example can be finally generated. Experiments show that the adversarial text examples generated by the proposed method not only successfully fool advanced DNN models, but also carry a watermark that can effectively verify the ownership and trace the source of the adversarial examples. Moreover, the watermark can still survive after attacked with adversarial example generation algorithms, which has shown the applicability and superiority." @default.
- W3211197554 created "2021-11-08" @default.
- W3211197554 creator A5049733139 @default.
- W3211197554 creator A5061288330 @default.
- W3211197554 creator A5071724015 @default.
- W3211197554 date "2021-10-25" @default.
- W3211197554 modified "2023-09-23" @default.
- W3211197554 title "Generating Watermarked Adversarial Texts" @default.
- W3211197554 cites W1524144700 @default.
- W3211197554 cites W1605292408 @default.
- W3211197554 cites W1901129140 @default.
- W3211197554 cites W1969109877 @default.
- W3211197554 cites W2076385485 @default.
- W3211197554 cites W2081580037 @default.
- W3211197554 cites W2135862109 @default.
- W3211197554 cites W2180612164 @default.
- W3211197554 cites W2194775991 @default.
- W3211197554 cites W2243397390 @default.
- W3211197554 cites W2250539671 @default.
- W3211197554 cites W2250861254 @default.
- W3211197554 cites W2251939518 @default.
- W3211197554 cites W2460937040 @default.
- W3211197554 cites W2485037161 @default.
- W3211197554 cites W2486441166 @default.
- W3211197554 cites W2525778437 @default.
- W3211197554 cites W2738015883 @default.
- W3211197554 cites W2767899794 @default.
- W3211197554 cites W2767951891 @default.
- W3211197554 cites W2782403400 @default.
- W3211197554 cites W2783113218 @default.
- W3211197554 cites W2790136966 @default.
- W3211197554 cites W2798139452 @default.
- W3211197554 cites W2798966449 @default.
- W3211197554 cites W2799007037 @default.
- W3211197554 cites W2807614607 @default.
- W3211197554 cites W2949128310 @default.
- W3211197554 cites W2950296219 @default.
- W3211197554 cites W2952730822 @default.
- W3211197554 cites W2962782614 @default.
- W3211197554 cites W2962784628 @default.
- W3211197554 cites W2963207607 @default.
- W3211197554 cites W2963341956 @default.
- W3211197554 cites W2963834268 @default.
- W3211197554 cites W2963918774 @default.
- W3211197554 cites W2964153729 @default.
- W3211197554 cites W2982756474 @default.
- W3211197554 cites W3088748086 @default.
- W3211197554 cites W3089357417 @default.
- W3211197554 cites W3135441826 @default.
- W3211197554 cites W3135872251 @default.
- W3211197554 cites W3171610440 @default.
- W3211197554 cites W41035042 @default.
- W3211197554 doi "https://doi.org/10.48550/arxiv.2110.12948" @default.
- W3211197554 hasPublicationYear "2021" @default.
- W3211197554 type Work @default.
- W3211197554 sameAs 3211197554 @default.
- W3211197554 citedByCount "0" @default.
- W3211197554 crossrefType "posted-content" @default.
- W3211197554 hasAuthorship W3211197554A5049733139 @default.
- W3211197554 hasAuthorship W3211197554A5061288330 @default.
- W3211197554 hasAuthorship W3211197554A5071724015 @default.
- W3211197554 hasBestOaLocation W32111975541 @default.
- W3211197554 hasConcept C104317684 @default.
- W3211197554 hasConcept C115961682 @default.
- W3211197554 hasConcept C138885662 @default.
- W3211197554 hasConcept C154945302 @default.
- W3211197554 hasConcept C164112704 @default.
- W3211197554 hasConcept C177264268 @default.
- W3211197554 hasConcept C185592680 @default.
- W3211197554 hasConcept C199360897 @default.
- W3211197554 hasConcept C204321447 @default.
- W3211197554 hasConcept C2984842247 @default.
- W3211197554 hasConcept C37736160 @default.
- W3211197554 hasConcept C41008148 @default.
- W3211197554 hasConcept C41895202 @default.
- W3211197554 hasConcept C50644808 @default.
- W3211197554 hasConcept C55493867 @default.
- W3211197554 hasConcept C63479239 @default.
- W3211197554 hasConcept C75291252 @default.
- W3211197554 hasConcept C80444323 @default.
- W3211197554 hasConcept C90805587 @default.
- W3211197554 hasConceptScore W3211197554C104317684 @default.
- W3211197554 hasConceptScore W3211197554C115961682 @default.
- W3211197554 hasConceptScore W3211197554C138885662 @default.
- W3211197554 hasConceptScore W3211197554C154945302 @default.
- W3211197554 hasConceptScore W3211197554C164112704 @default.
- W3211197554 hasConceptScore W3211197554C177264268 @default.
- W3211197554 hasConceptScore W3211197554C185592680 @default.
- W3211197554 hasConceptScore W3211197554C199360897 @default.
- W3211197554 hasConceptScore W3211197554C204321447 @default.
- W3211197554 hasConceptScore W3211197554C2984842247 @default.
- W3211197554 hasConceptScore W3211197554C37736160 @default.
- W3211197554 hasConceptScore W3211197554C41008148 @default.
- W3211197554 hasConceptScore W3211197554C41895202 @default.
- W3211197554 hasConceptScore W3211197554C50644808 @default.
- W3211197554 hasConceptScore W3211197554C55493867 @default.
- W3211197554 hasConceptScore W3211197554C63479239 @default.
- W3211197554 hasConceptScore W3211197554C75291252 @default.
- W3211197554 hasConceptScore W3211197554C80444323 @default.
- W3211197554 hasConceptScore W3211197554C90805587 @default.