FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309398410> ?p ?o ?g. }

• W4309398410 abstract "In online medium such as opinion column in Bloomberg, The Guardian and Western Journal, aspiring writers post their writings for various reasons with their names often proudly open. However, it may occur that such a writer wants to write in other venues anonymously or under a pseudonym (e.g., activist, whistle-blower). However, if an attacker has already built an accurate authorship attribution (AA) model based off of the writings from such platforms, attributing an anonymous writing to the known authorship is possible. Therefore, in this work, we ask a question can one make the writings and texts, T, in the open spaces such as opinion sharing platforms unattributable so that AA models trained from T cannot attribute authorship well? Toward this question, we present a novel solution, UPTON, that exploits textual data poisoning method to disturb the training process of AA models. UPTON uses data poisoning to destroy the authorship feature only in training samples by perturbing them, and try to make released textual data unlearnable on deep neuron networks. It is different from previous obfuscation works, that use adversarial attack to modify the test samples and mislead an AA model, and also the backdoor works, which use trigger words both in test and training samples and only change the model output when trigger words occur. Using four authorship datasets (e.g., IMDb10, IMDb64, Enron and WJO), then, we present empirical validation where: (1)UPTON is able to downgrade the test accuracy to about 30% with carefully designed target-selection methods. (2)UPTON poisoning is able to preserve most of the original semantics. The BERTSCORE between the clean and UPTON poisoned texts are higher than 0.95. The number is very closed to 1.00, which means no sematic change. (3)UPTON is also robust towards spelling correction systems." @default.
• W4309398410 created "2022-11-26" @default.
• W4309398410 creator A5024109615 @default.
• W4309398410 creator A5026480264 @default.
• W4309398410 creator A5054483605 @default.
• W4309398410 date "2022-11-17" @default.
• W4309398410 modified "2023-09-29" @default.
• W4309398410 title "UPTON: Unattributable Authorship Text via Data Poisoning" @default.
• W4309398410 doi "https://doi.org/10.48550/arxiv.2211.09717" @default.
• W4309398410 hasPublicationYear "2022" @default.
• W4309398410 type Work @default.
• W4309398410 citedByCount "0" @default.
• W4309398410 crossrefType "posted-content" @default.
• W4309398410 hasAuthorship W4309398410A5024109615 @default.
• W4309398410 hasAuthorship W4309398410A5026480264 @default.
• W4309398410 hasAuthorship W4309398410A5054483605 @default.
• W4309398410 hasBestOaLocation W43093984101 @default.
• W4309398410 hasConcept C151730666 @default.
• W4309398410 hasConcept C154945302 @default.
• W4309398410 hasConcept C17744445 @default.
• W4309398410 hasConcept C199539241 @default.
• W4309398410 hasConcept C2776021475 @default.
• W4309398410 hasConcept C2777267654 @default.
• W4309398410 hasConcept C2779628075 @default.
• W4309398410 hasConcept C3020202489 @default.
• W4309398410 hasConcept C38652104 @default.
• W4309398410 hasConcept C41008148 @default.
• W4309398410 hasConcept C86803240 @default.
• W4309398410 hasConceptScore W4309398410C151730666 @default.
• W4309398410 hasConceptScore W4309398410C154945302 @default.
• W4309398410 hasConceptScore W4309398410C17744445 @default.
• W4309398410 hasConceptScore W4309398410C199539241 @default.
• W4309398410 hasConceptScore W4309398410C2776021475 @default.
• W4309398410 hasConceptScore W4309398410C2777267654 @default.
• W4309398410 hasConceptScore W4309398410C2779628075 @default.
• W4309398410 hasConceptScore W4309398410C3020202489 @default.
• W4309398410 hasConceptScore W4309398410C38652104 @default.
• W4309398410 hasConceptScore W4309398410C41008148 @default.
• W4309398410 hasConceptScore W4309398410C86803240 @default.
• W4309398410 hasLocation W43093984101 @default.
• W4309398410 hasOpenAccess W4309398410 @default.
• W4309398410 hasPrimaryLocation W43093984101 @default.
• W4309398410 hasRelatedWork W179961936 @default.
• W4309398410 hasRelatedWork W1851713931 @default.
• W4309398410 hasRelatedWork W2037545913 @default.
• W4309398410 hasRelatedWork W2465435719 @default.
• W4309398410 hasRelatedWork W2748952813 @default.
• W4309398410 hasRelatedWork W2899084033 @default.
• W4309398410 hasRelatedWork W2900149775 @default.
• W4309398410 hasRelatedWork W2963230048 @default.
• W4309398410 hasRelatedWork W2963505936 @default.
• W4309398410 hasRelatedWork W4289303923 @default.
• W4309398410 isParatext "false" @default.
• W4309398410 isRetracted "false" @default.
• W4309398410 workType "article" @default.