FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290717778> ?p ?o ?g. }

• W4290717778 endingPage "83970" @default.
• W4290717778 startingPage "83949" @default.
• W4290717778 abstract "Machine learning (ML) algorithms are nowadays widely adopted in different contexts to perform autonomous decisions and predictions. Due to the high volume of data shared in the recent years, ML algorithms are more accurate and reliable since training and testing phases are more precise. An important concept to analyze when defining ML algorithms concerns adversarial machine learning attacks. These attacks aim to create manipulated datasets to mislead ML algorithm decisions. In this work, we propose new approaches able to detect and mitigate malicious adversarial machine learning attacks against a ML system. In particular, we investigate the Carlini-Wagner (CW), the fast gradient sign method (FGSM) and the Jacobian based saliency map (JSMA) attacks. The aim of this work is to exploit detection algorithms as countermeasures to these attacks. Initially, we performed some tests by using canonical ML algorithms with a hyperparameters optimization to improve metrics. Then, we adopt original reliable AI algorithms, either based on eXplainable AI (Logic Learning Machine) or Support Vector Data Description (SVDD). The obtained results show how the classical algorithms may fail to identify an adversarial attack, while the reliable AI methodologies are more prone to correctly detect a possible adversarial machine learning attack. The evaluation of the proposed methodology was carried out in terms of good balance between FPR and FNR on real world application datasets: Domain Name System (DNS) tunneling, Vehicle Platooning and Remaining Useful Life (RUL). In addition, a statistical analysis was performed to improve the robustness of the trained models, including evaluating their performance in terms of runtime and memory consumption." @default.
• W4290717778 created "2022-08-09" @default.
• W4290717778 creator A5030029772 @default.
• W4290717778 creator A5049925516 @default.
• W4290717778 creator A5051577928 @default.
• W4290717778 creator A5052730290 @default.
• W4290717778 creator A5059792906 @default.
• W4290717778 date "2022-01-01" @default.
• W4290717778 modified "2023-09-28" @default.
• W4290717778 title "eXplainable and Reliable Against Adversarial Machine Learning in Data Analytics" @default.
• W4290717778 cites W1490349213 @default.
• W4290717778 cites W1907846276 @default.
• W4290717778 cites W1966517947 @default.
• W4290717778 cites W1970088130 @default.
• W4290717778 cites W2094590527 @default.
• W4290717778 cites W2100294832 @default.
• W4290717778 cites W2104770855 @default.
• W4290717778 cites W2120841219 @default.
• W4290717778 cites W2180612164 @default.
• W4290717778 cites W2243397390 @default.
• W4290717778 cites W2411951812 @default.
• W4290717778 cites W2734809238 @default.
• W4290717778 cites W2793714280 @default.
• W4290717778 cites W2818212751 @default.
• W4290717778 cites W2844602024 @default.
• W4290717778 cites W2852300932 @default.
• W4290717778 cites W2888401638 @default.
• W4290717778 cites W2895812865 @default.
• W4290717778 cites W2919491917 @default.
• W4290717778 cites W2924551358 @default.
• W4290717778 cites W2949676527 @default.
• W4290717778 cites W2963165251 @default.
• W4290717778 cites W2963461515 @default.
• W4290717778 cites W2963857521 @default.
• W4290717778 cites W2964082701 @default.
• W4290717778 cites W2964301649 @default.
• W4290717778 cites W2971480956 @default.
• W4290717778 cites W2981731882 @default.
• W4290717778 cites W2999097465 @default.
• W4290717778 cites W3009195050 @default.
• W4290717778 cites W3013520104 @default.
• W4290717778 cites W3041751968 @default.
• W4290717778 cites W3042739153 @default.
• W4290717778 cites W3098620325 @default.
• W4290717778 cites W3123744197 @default.
• W4290717778 cites W3133233862 @default.
• W4290717778 cites W3135028703 @default.
• W4290717778 cites W3164220323 @default.
• W4290717778 cites W3165102474 @default.
• W4290717778 cites W3172336096 @default.
• W4290717778 cites W3187628345 @default.
• W4290717778 cites W3188783384 @default.
• W4290717778 cites W3191717083 @default.
• W4290717778 cites W3209109159 @default.
• W4290717778 cites W4247200422 @default.
• W4290717778 doi "https://doi.org/10.1109/access.2022.3197299" @default.
• W4290717778 hasPublicationYear "2022" @default.
• W4290717778 type Work @default.
• W4290717778 citedByCount "4" @default.
• W4290717778 countsByYear W42907177782023 @default.
• W4290717778 crossrefType "journal-article" @default.
• W4290717778 hasAuthorship W4290717778A5030029772 @default.
• W4290717778 hasAuthorship W4290717778A5049925516 @default.
• W4290717778 hasAuthorship W4290717778A5051577928 @default.
• W4290717778 hasAuthorship W4290717778A5052730290 @default.
• W4290717778 hasAuthorship W4290717778A5059792906 @default.
• W4290717778 hasBestOaLocation W42907177781 @default.
• W4290717778 hasConcept C104317684 @default.
• W4290717778 hasConcept C115903097 @default.
• W4290717778 hasConcept C119857082 @default.
• W4290717778 hasConcept C12267149 @default.
• W4290717778 hasConcept C154945302 @default.
• W4290717778 hasConcept C165696696 @default.
• W4290717778 hasConcept C185592680 @default.
• W4290717778 hasConcept C2778403875 @default.
• W4290717778 hasConcept C37736160 @default.
• W4290717778 hasConcept C38652104 @default.
• W4290717778 hasConcept C41008148 @default.
• W4290717778 hasConcept C50644808 @default.
• W4290717778 hasConcept C55493867 @default.
• W4290717778 hasConcept C63479239 @default.
• W4290717778 hasConcept C8642999 @default.
• W4290717778 hasConceptScore W4290717778C104317684 @default.
• W4290717778 hasConceptScore W4290717778C115903097 @default.
• W4290717778 hasConceptScore W4290717778C119857082 @default.
• W4290717778 hasConceptScore W4290717778C12267149 @default.
• W4290717778 hasConceptScore W4290717778C154945302 @default.
• W4290717778 hasConceptScore W4290717778C165696696 @default.
• W4290717778 hasConceptScore W4290717778C185592680 @default.
• W4290717778 hasConceptScore W4290717778C2778403875 @default.
• W4290717778 hasConceptScore W4290717778C37736160 @default.
• W4290717778 hasConceptScore W4290717778C38652104 @default.
• W4290717778 hasConceptScore W4290717778C41008148 @default.
• W4290717778 hasConceptScore W4290717778C50644808 @default.
• W4290717778 hasConceptScore W4290717778C55493867 @default.
• W4290717778 hasConceptScore W4290717778C63479239 @default.
• W4290717778 hasConceptScore W4290717778C8642999 @default.
• W4290717778 hasLocation W42907177781 @default.

• next