Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311559671> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4311559671 abstract "There has been a concurrent significant improvement in the medical images used to facilitate diagnosis and the performance of machine learning techniques to perform tasks such as classification, detection, and segmentation in recent years. As a result, a rapid increase in the usage of such systems can be observed in the healthcare industry, for instance in the form of medical image classification systems, where these models have achieved diagnostic parity with human physicians. One such application where this can be observed is in computer vision tasks such as the classification of skin lesions in dermatoscopic images. However, as stakeholders in the healthcare industry, such as insurance companies, continue to invest extensively in machine learning infrastructure, it becomes increasingly important to understand the vulnerabilities in such systems. Due to the highly critical nature of the tasks being carried out by these machine learning models, it is necessary to analyze techniques that could be used to take advantage of these vulnerabilities and methods to defend against them. This paper explores common adversarial attack techniques. The Fast Sign Gradient Method and Projected Descent Gradient are used against a Convolutional Neural Network trained to classify dermatoscopic images of skin lesions. Following that, it also discusses one of the most popular adversarial defense techniques, adversarial training. The performance of the model that has been trained on adversarial examples is then tested against the previously mentioned attacks, and recommendations to improve neural networks robustness are thus provided based on the results of the experiment." @default.
- W4311559671 created "2022-12-27" @default.
- W4311559671 creator A5014327880 @default.
- W4311559671 creator A5027473449 @default.
- W4311559671 creator A5060353947 @default.
- W4311559671 creator A5074566998 @default.
- W4311559671 creator A5081923364 @default.
- W4311559671 date "2022-12-13" @default.
- W4311559671 modified "2023-09-26" @default.
- W4311559671 title "Adversarial Attacks and Defences for Skin Cancer Classification" @default.
- W4311559671 doi "https://doi.org/10.48550/arxiv.2212.06822" @default.
- W4311559671 hasPublicationYear "2022" @default.
- W4311559671 type Work @default.
- W4311559671 citedByCount "0" @default.
- W4311559671 crossrefType "posted-content" @default.
- W4311559671 hasAuthorship W4311559671A5014327880 @default.
- W4311559671 hasAuthorship W4311559671A5027473449 @default.
- W4311559671 hasAuthorship W4311559671A5060353947 @default.
- W4311559671 hasAuthorship W4311559671A5074566998 @default.
- W4311559671 hasAuthorship W4311559671A5081923364 @default.
- W4311559671 hasBestOaLocation W43115596711 @default.
- W4311559671 hasConcept C104317684 @default.
- W4311559671 hasConcept C108583219 @default.
- W4311559671 hasConcept C115961682 @default.
- W4311559671 hasConcept C119857082 @default.
- W4311559671 hasConcept C154945302 @default.
- W4311559671 hasConcept C160735492 @default.
- W4311559671 hasConcept C162324750 @default.
- W4311559671 hasConcept C185592680 @default.
- W4311559671 hasConcept C2778403875 @default.
- W4311559671 hasConcept C2984842247 @default.
- W4311559671 hasConcept C37736160 @default.
- W4311559671 hasConcept C41008148 @default.
- W4311559671 hasConcept C50522688 @default.
- W4311559671 hasConcept C50644808 @default.
- W4311559671 hasConcept C55493867 @default.
- W4311559671 hasConcept C63479239 @default.
- W4311559671 hasConcept C75294576 @default.
- W4311559671 hasConcept C81363708 @default.
- W4311559671 hasConcept C89600930 @default.
- W4311559671 hasConceptScore W4311559671C104317684 @default.
- W4311559671 hasConceptScore W4311559671C108583219 @default.
- W4311559671 hasConceptScore W4311559671C115961682 @default.
- W4311559671 hasConceptScore W4311559671C119857082 @default.
- W4311559671 hasConceptScore W4311559671C154945302 @default.
- W4311559671 hasConceptScore W4311559671C160735492 @default.
- W4311559671 hasConceptScore W4311559671C162324750 @default.
- W4311559671 hasConceptScore W4311559671C185592680 @default.
- W4311559671 hasConceptScore W4311559671C2778403875 @default.
- W4311559671 hasConceptScore W4311559671C2984842247 @default.
- W4311559671 hasConceptScore W4311559671C37736160 @default.
- W4311559671 hasConceptScore W4311559671C41008148 @default.
- W4311559671 hasConceptScore W4311559671C50522688 @default.
- W4311559671 hasConceptScore W4311559671C50644808 @default.
- W4311559671 hasConceptScore W4311559671C55493867 @default.
- W4311559671 hasConceptScore W4311559671C63479239 @default.
- W4311559671 hasConceptScore W4311559671C75294576 @default.
- W4311559671 hasConceptScore W4311559671C81363708 @default.
- W4311559671 hasConceptScore W4311559671C89600930 @default.
- W4311559671 hasLocation W43115596711 @default.
- W4311559671 hasOpenAccess W4311559671 @default.
- W4311559671 hasPrimaryLocation W43115596711 @default.
- W4311559671 hasRelatedWork W2610321374 @default.
- W4311559671 hasRelatedWork W2755252132 @default.
- W4311559671 hasRelatedWork W2799614062 @default.
- W4311559671 hasRelatedWork W2952919291 @default.
- W4311559671 hasRelatedWork W3101705166 @default.
- W4311559671 hasRelatedWork W3193857078 @default.
- W4311559671 hasRelatedWork W3199527517 @default.
- W4311559671 hasRelatedWork W3208423683 @default.
- W4311559671 hasRelatedWork W4293211451 @default.
- W4311559671 hasRelatedWork W4311257506 @default.
- W4311559671 isParatext "false" @default.
- W4311559671 isRetracted "false" @default.
- W4311559671 workType "article" @default.