FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204683301> ?p ?o ?g. }

• W3204683301 endingPage "4938" @default.
• W3204683301 startingPage "4924" @default.
• W3204683301 abstract "Machine Learning methods are playing a vital role in combating ever-evolving threats in the cybersecurity domain. Explanation methods that shed light on the decision process of black-box classifiers are one of the biggest drivers in the successful adoption of these models. Explaining predictions that address ‘Why?/Why Not?’ questions help users/stakeholders/analysts understand and accept the predicted outputs with confidence and build trust. Counterfactual explanations are gaining popularity as an alternative method to help users to not only understand the decisions of black-box models (why?) but also to provide a mechanism to highlight mutually exclusive data instances that would change the outcomes (why not?). Recent Explainable Artificial Intelligence literature has focused on three main areas: (a) creating and improving explainability methods that help users better understand how the internal of ML models work as well as their outputs; (b) attacks on interpreters with a white-box setting; (c) defining the relevant properties, metrics of explanations generated by models. Nevertheless, there is no thorough study of how the model explanations can introduce new attack surfaces to the underlying systems. A motivated adversary can leverage the information provided by explanations to launch membership inference, and model extraction attacks to compromise the overall privacy of the system. Similarly, explanations can also facilitate powerful evasion attacks such as poisoning and back door attacks. In this paper, we cover this gap by tackling various cybersecurity properties and threat models related to counterfactual explanations. We propose a new black-box attack that leverages Explainable Artificial Intelligence (XAI) methods to compromise the confidentiality and privacy properties of underlying classifiers. We validate our approach with datasets and models used in the cyber security domain to demonstrate that our method achieves the attacker’s goal under threat models which reflect the real-world settings." @default.
• W3204683301 created "2021-10-11" @default.
• W3204683301 creator A5073189627 @default.
• W3204683301 creator A5083053959 @default.
• W3204683301 date "2021-01-01" @default.
• W3204683301 modified "2023-10-18" @default.
• W3204683301 title "Adversarial XAI Methods in Cybersecurity" @default.
• W3204683301 cites W1523207696 @default.
• W3204683301 cites W1966912382 @default.
• W3204683301 cites W2095577883 @default.
• W3204683301 cites W2135143063 @default.
• W3204683301 cites W2535690855 @default.
• W3204683301 cites W2591919231 @default.
• W3204683301 cites W2603766943 @default.
• W3204683301 cites W2746600820 @default.
• W3204683301 cites W2753783305 @default.
• W3204683301 cites W2789828921 @default.
• W3204683301 cites W2792991556 @default.
• W3204683301 cites W2795530988 @default.
• W3204683301 cites W2890324916 @default.
• W3204683301 cites W2890416412 @default.
• W3204683301 cites W2897865027 @default.
• W3204683301 cites W2903650079 @default.
• W3204683301 cites W2945295328 @default.
• W3204683301 cites W2954978443 @default.
• W3204683301 cites W2962711307 @default.
• W3204683301 cites W2962763344 @default.
• W3204683301 cites W2962772482 @default.
• W3204683301 cites W2963125461 @default.
• W3204683301 cites W2963303354 @default.
• W3204683301 cites W2963560987 @default.
• W3204683301 cites W2964303497 @default.
• W3204683301 cites W2964449086 @default.
• W3204683301 cites W2966362896 @default.
• W3204683301 cites W2968455244 @default.
• W3204683301 cites W2981731882 @default.
• W3204683301 cites W2995528912 @default.
• W3204683301 cites W3003166972 @default.
• W3204683301 cites W3026235644 @default.
• W3204683301 cites W3090855408 @default.
• W3204683301 cites W3091163785 @default.
• W3204683301 cites W3097157638 @default.
• W3204683301 cites W3162836204 @default.
• W3204683301 cites W4245123454 @default.
• W3204683301 cites W4247200422 @default.
• W3204683301 cites W4288414189 @default.
• W3204683301 cites W4296978576 @default.
• W3204683301 doi "https://doi.org/10.1109/tifs.2021.3117075" @default.
• W3204683301 hasPublicationYear "2021" @default.
• W3204683301 type Work @default.
• W3204683301 sameAs 3204683301 @default.
• W3204683301 citedByCount "19" @default.
• W3204683301 countsByYear W32046833012022 @default.
• W3204683301 countsByYear W32046833012023 @default.
• W3204683301 crossrefType "journal-article" @default.
• W3204683301 hasAuthorship W3204683301A5073189627 @default.
• W3204683301 hasAuthorship W3204683301A5083053959 @default.
• W3204683301 hasBestOaLocation W32046833011 @default.
• W3204683301 hasConcept C108650721 @default.
• W3204683301 hasConcept C111472728 @default.
• W3204683301 hasConcept C138885662 @default.
• W3204683301 hasConcept C144024400 @default.
• W3204683301 hasConcept C153083717 @default.
• W3204683301 hasConcept C154945302 @default.
• W3204683301 hasConcept C15744967 @default.
• W3204683301 hasConcept C2522767166 @default.
• W3204683301 hasConcept C2776214188 @default.
• W3204683301 hasConcept C2780586970 @default.
• W3204683301 hasConcept C36289849 @default.
• W3204683301 hasConcept C37736160 @default.
• W3204683301 hasConcept C38652104 @default.
• W3204683301 hasConcept C41008148 @default.
• W3204683301 hasConcept C41065033 @default.
• W3204683301 hasConcept C46355384 @default.
• W3204683301 hasConcept C517642484 @default.
• W3204683301 hasConcept C77805123 @default.
• W3204683301 hasConcept C94966114 @default.
• W3204683301 hasConceptScore W3204683301C108650721 @default.
• W3204683301 hasConceptScore W3204683301C111472728 @default.
• W3204683301 hasConceptScore W3204683301C138885662 @default.
• W3204683301 hasConceptScore W3204683301C144024400 @default.
• W3204683301 hasConceptScore W3204683301C153083717 @default.
• W3204683301 hasConceptScore W3204683301C154945302 @default.
• W3204683301 hasConceptScore W3204683301C15744967 @default.
• W3204683301 hasConceptScore W3204683301C2522767166 @default.
• W3204683301 hasConceptScore W3204683301C2776214188 @default.
• W3204683301 hasConceptScore W3204683301C2780586970 @default.
• W3204683301 hasConceptScore W3204683301C36289849 @default.
• W3204683301 hasConceptScore W3204683301C37736160 @default.
• W3204683301 hasConceptScore W3204683301C38652104 @default.
• W3204683301 hasConceptScore W3204683301C41008148 @default.
• W3204683301 hasConceptScore W3204683301C41065033 @default.
• W3204683301 hasConceptScore W3204683301C46355384 @default.
• W3204683301 hasConceptScore W3204683301C517642484 @default.
• W3204683301 hasConceptScore W3204683301C77805123 @default.
• W3204683301 hasConceptScore W3204683301C94966114 @default.
• W3204683301 hasLocation W32046833011 @default.
• W3204683301 hasOpenAccess W3204683301 @default.

• next