Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385280807> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4385280807 endingPage "245" @default.
- W4385280807 startingPage "227" @default.
- W4385280807 abstract "Artificial Intelligence (AI) has witnessed significant advancements in recent years, enabling its widespread adoption across various domains. However, this progress has also given rise to new challenges, particularly in the context of adversarial machine learning. Adversarial attacks exploit vulnerabilities in AI models, resulting in their misclassification or misbehaviour. To address this critical issue, it is crucial to develop trustworthy AI systems that can withstand such adversarial threats. This paper presents a comprehensive study that covers the types of adversarial machine learning cyber-attacks, methods employed by adversaries to launch such attacks, effective defence mechanisms, and potential future directions in the field. It starts by exploring various types of adversarial ML attacks, characteristics and potential consequences of each attack type, emphasizing the risks they pose to privacy, security, and fairness in AI systems and delving into the methods employed by adversaries to launch adversarial ML attacks. By understanding the tactics used by adversaries, researchers and practitioners can develop robust defence mechanisms that can withstand these attacks. Building upon this understanding, a range of defence strategies can be invented for defending against adversarial ML attacks and emerging research areas, such as the integration of secure multi-party computation, differential privacy, and federated learning are used to enhance the resilience of AI models. By understanding the nature of adversarial attacks and implementing effective defence strategies, AI systems can be fortified against malicious manipulations. The findings of this study contribute to the development of trustworthy AI systems, ensuring their resilience, transparency, and fairness." @default.
- W4385280807 created "2023-07-27" @default.
- W4385280807 creator A5053397993 @default.
- W4385280807 creator A5069081293 @default.
- W4385280807 date "2023-09-01" @default.
- W4385280807 modified "2023-09-27" @default.
- W4385280807 title "Trustworthy AI Principles to Face Adversarial Machine Learning: A Novel Study" @default.
- W4385280807 cites W2077414053 @default.
- W4385280807 cites W2095577883 @default.
- W4385280807 cites W2159196732 @default.
- W4385280807 cites W2930249865 @default.
- W4385280807 cites W2996623839 @default.
- W4385280807 cites W3015481738 @default.
- W4385280807 cites W3031351653 @default.
- W4385280807 cites W3116515605 @default.
- W4385280807 cites W3123744197 @default.
- W4385280807 cites W3191297416 @default.
- W4385280807 cites W4206541522 @default.
- W4385280807 cites W4382318772 @default.
- W4385280807 doi "https://doi.org/10.36548/jaicn.2023.3.002" @default.
- W4385280807 hasPublicationYear "2023" @default.
- W4385280807 type Work @default.
- W4385280807 citedByCount "0" @default.
- W4385280807 crossrefType "journal-article" @default.
- W4385280807 hasAuthorship W4385280807A5053397993 @default.
- W4385280807 hasAuthorship W4385280807A5069081293 @default.
- W4385280807 hasConcept C121332964 @default.
- W4385280807 hasConcept C151730666 @default.
- W4385280807 hasConcept C153701036 @default.
- W4385280807 hasConcept C154945302 @default.
- W4385280807 hasConcept C165696696 @default.
- W4385280807 hasConcept C2522767166 @default.
- W4385280807 hasConcept C2778403875 @default.
- W4385280807 hasConcept C2779343474 @default.
- W4385280807 hasConcept C2779585090 @default.
- W4385280807 hasConcept C2780233690 @default.
- W4385280807 hasConcept C37736160 @default.
- W4385280807 hasConcept C38652104 @default.
- W4385280807 hasConcept C41008148 @default.
- W4385280807 hasConcept C86803240 @default.
- W4385280807 hasConcept C97355855 @default.
- W4385280807 hasConceptScore W4385280807C121332964 @default.
- W4385280807 hasConceptScore W4385280807C151730666 @default.
- W4385280807 hasConceptScore W4385280807C153701036 @default.
- W4385280807 hasConceptScore W4385280807C154945302 @default.
- W4385280807 hasConceptScore W4385280807C165696696 @default.
- W4385280807 hasConceptScore W4385280807C2522767166 @default.
- W4385280807 hasConceptScore W4385280807C2778403875 @default.
- W4385280807 hasConceptScore W4385280807C2779343474 @default.
- W4385280807 hasConceptScore W4385280807C2779585090 @default.
- W4385280807 hasConceptScore W4385280807C2780233690 @default.
- W4385280807 hasConceptScore W4385280807C37736160 @default.
- W4385280807 hasConceptScore W4385280807C38652104 @default.
- W4385280807 hasConceptScore W4385280807C41008148 @default.
- W4385280807 hasConceptScore W4385280807C86803240 @default.
- W4385280807 hasConceptScore W4385280807C97355855 @default.
- W4385280807 hasIssue "3" @default.
- W4385280807 hasLocation W43852808071 @default.
- W4385280807 hasOpenAccess W4385280807 @default.
- W4385280807 hasPrimaryLocation W43852808071 @default.
- W4385280807 hasRelatedWork W286553814 @default.
- W4385280807 hasRelatedWork W3124408655 @default.
- W4385280807 hasRelatedWork W3160683614 @default.
- W4385280807 hasRelatedWork W4248052496 @default.
- W4385280807 hasRelatedWork W4251088474 @default.
- W4385280807 hasRelatedWork W4297785512 @default.
- W4385280807 hasRelatedWork W4304014839 @default.
- W4385280807 hasRelatedWork W4311711335 @default.
- W4385280807 hasRelatedWork W4383468834 @default.
- W4385280807 hasRelatedWork W4287613778 @default.
- W4385280807 hasVolume "5" @default.
- W4385280807 isParatext "false" @default.
- W4385280807 isRetracted "false" @default.
- W4385280807 workType "article" @default.