Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385571712> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4385571712 abstract "When textual classifiers are deployed in safety-critical workflows, they must withstand the onslaught of AI-enabled model confusion caused by adversarial examples with minor alterations. In this paper, the main objective is to provide a formal verification framework, called TextVerifier, with certifiable guarantees on deep neural networks in natural language processing against word-level alteration attacks. We aim to provide an approximation of the maximal safe radius by deriving provable bounds both mathematically and automatically, where a minimum word-level L_0 distance is quantified as a guarantee for the classification invariance of victim models. Here, we illustrate three strengths of our strategy: i) certifiable guarantee: effective verification with convergence to ensure approximation of maximal safe radius with tight bounds ultimately; ii) high-efficiency: it yields an efficient speed edge by a novel parallelization strategy that can process a set of candidate texts simultaneously on GPUs; and iii) reliable anytime estimation: the verification can return intermediate bounds, and robustness estimates that are gradually, but strictly, improved as the computation proceeds. Furthermore, experiments are conducted on text classification on four datasets over three victim models to demonstrate the validity of tightening bounds. Our tool TextVerifier is available at https://github.com/TrustAI/TextVerifer." @default.
- W4385571712 created "2023-08-05" @default.
- W4385571712 creator A5023777406 @default.
- W4385571712 creator A5074225885 @default.
- W4385571712 date "2023-01-01" @default.
- W4385571712 modified "2023-09-24" @default.
- W4385571712 title "TextVerifier: Robustness Verification for Textual Classifiers with Certifiable Guarantees" @default.
- W4385571712 doi "https://doi.org/10.18653/v1/2023.findings-acl.267" @default.
- W4385571712 hasPublicationYear "2023" @default.
- W4385571712 type Work @default.
- W4385571712 citedByCount "0" @default.
- W4385571712 crossrefType "proceedings-article" @default.
- W4385571712 hasAuthorship W4385571712A5023777406 @default.
- W4385571712 hasAuthorship W4385571712A5074225885 @default.
- W4385571712 hasBestOaLocation W43855717121 @default.
- W4385571712 hasConcept C104317684 @default.
- W4385571712 hasConcept C111498074 @default.
- W4385571712 hasConcept C11413529 @default.
- W4385571712 hasConcept C154945302 @default.
- W4385571712 hasConcept C173608175 @default.
- W4385571712 hasConcept C185592680 @default.
- W4385571712 hasConcept C41008148 @default.
- W4385571712 hasConcept C45374587 @default.
- W4385571712 hasConcept C55493867 @default.
- W4385571712 hasConcept C63479239 @default.
- W4385571712 hasConcept C68339613 @default.
- W4385571712 hasConcept C80444323 @default.
- W4385571712 hasConceptScore W4385571712C104317684 @default.
- W4385571712 hasConceptScore W4385571712C111498074 @default.
- W4385571712 hasConceptScore W4385571712C11413529 @default.
- W4385571712 hasConceptScore W4385571712C154945302 @default.
- W4385571712 hasConceptScore W4385571712C173608175 @default.
- W4385571712 hasConceptScore W4385571712C185592680 @default.
- W4385571712 hasConceptScore W4385571712C41008148 @default.
- W4385571712 hasConceptScore W4385571712C45374587 @default.
- W4385571712 hasConceptScore W4385571712C55493867 @default.
- W4385571712 hasConceptScore W4385571712C63479239 @default.
- W4385571712 hasConceptScore W4385571712C68339613 @default.
- W4385571712 hasConceptScore W4385571712C80444323 @default.
- W4385571712 hasLocation W43855717121 @default.
- W4385571712 hasOpenAccess W4385571712 @default.
- W4385571712 hasPrimaryLocation W43855717121 @default.
- W4385571712 hasRelatedWork W1589376391 @default.
- W4385571712 hasRelatedWork W2006943202 @default.
- W4385571712 hasRelatedWork W2007449167 @default.
- W4385571712 hasRelatedWork W2051711022 @default.
- W4385571712 hasRelatedWork W2090033344 @default.
- W4385571712 hasRelatedWork W2391299576 @default.
- W4385571712 hasRelatedWork W2403150446 @default.
- W4385571712 hasRelatedWork W2591281746 @default.
- W4385571712 hasRelatedWork W3040412425 @default.
- W4385571712 hasRelatedWork W1506942559 @default.
- W4385571712 isParatext "false" @default.
- W4385571712 isRetracted "false" @default.
- W4385571712 workType "article" @default.