FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285404754> ?p ?o ?g. }

• W4285404754 endingPage "118101" @default.
• W4285404754 startingPage "118101" @default.
• W4285404754 abstract "For the past decade, machine learning technology has increasingly become popular and it has been contributing to many areas that have the potential to influence the society considerably. Generally, machine learning is used by various industries to enhance their performances. Moreover, machine learning algorithms are used to solve some hard problems of systems that may contain very critical information. This makes machine learning algorithms a target of adversaries, which is an important problem for systems that use such algorithms. Therefore, it is significant to determine the performance and the robustness of a machine learning algorithm against attacks. In this paper, we analyze empirically the robustness and performances of six machine learning algorithms against two types of adversarial attacks by using four different datasets and three metrics. In our experiments, we analyze the robustness of Support Vector Machine, Stochastic Gradient Descent, Logistic Regression, Random Forest, Gaussian Naive Bayes, and K-Nearest Neighbor algorithms to create learning models. We observe their performances in spam, botnet, malware, and cancer detection datasets when we launch adversarial attacks against these environments. We use data poisoning for manipulating training data during adversarial attacks, which are random label flipping and distance-based label flipping attacks. We analyze the performance of each algorithm for a specific dataset by modifying the amount of poisoned data and analyzing behaviors of accuracy rate, f1-score, and AUC score. Analyses results show that machine learning algorithms have various performance results and robustness under different adversarial attacks. Moreover, machine learning algorithms are affected differently in each stage of an adversarial attacks. Furthermore, the behavior of a machine learning algorithm highly depends on the type of the dataset. On the other hand, some machine learning algorithms have better robustness and performance results against adversarial attacks for almost all datasets." @default.
• W4285404754 created "2022-07-14" @default.
• W4285404754 creator A5036243810 @default.
• W4285404754 creator A5040808125 @default.
• W4285404754 date "2022-12-01" @default.
• W4285404754 modified "2023-10-17" @default.
• W4285404754 title "Data poisoning attacks against machine learning algorithms" @default.
• W4285404754 cites W2107397716 @default.
• W4285404754 cites W2146211964 @default.
• W4285404754 cites W2167460663 @default.
• W4285404754 cites W2775904954 @default.
• W4285404754 cites W2801802177 @default.
• W4285404754 cites W2844602024 @default.
• W4285404754 cites W2899861195 @default.
• W4285404754 cites W2907236248 @default.
• W4285404754 cites W2949836779 @default.
• W4285404754 cites W2952766703 @default.
• W4285404754 cites W2980573810 @default.
• W4285404754 cites W2981446616 @default.
• W4285404754 cites W3038342492 @default.
• W4285404754 cites W3048339221 @default.
• W4285404754 cites W3103557498 @default.
• W4285404754 doi "https://doi.org/10.1016/j.eswa.2022.118101" @default.
• W4285404754 hasPublicationYear "2022" @default.
• W4285404754 type Work @default.
• W4285404754 citedByCount "8" @default.
• W4285404754 countsByYear W42854047542022 @default.
• W4285404754 countsByYear W42854047542023 @default.
• W4285404754 crossrefType "journal-article" @default.
• W4285404754 hasAuthorship W4285404754A5036243810 @default.
• W4285404754 hasAuthorship W4285404754A5040808125 @default.
• W4285404754 hasConcept C104317684 @default.
• W4285404754 hasConcept C110083411 @default.
• W4285404754 hasConcept C11413529 @default.
• W4285404754 hasConcept C115903097 @default.
• W4285404754 hasConcept C119857082 @default.
• W4285404754 hasConcept C12267149 @default.
• W4285404754 hasConcept C154945302 @default.
• W4285404754 hasConcept C169258074 @default.
• W4285404754 hasConcept C185592680 @default.
• W4285404754 hasConcept C206688291 @default.
• W4285404754 hasConcept C2778403875 @default.
• W4285404754 hasConcept C37736160 @default.
• W4285404754 hasConcept C41008148 @default.
• W4285404754 hasConcept C50644808 @default.
• W4285404754 hasConcept C52001869 @default.
• W4285404754 hasConcept C55493867 @default.
• W4285404754 hasConcept C63479239 @default.
• W4285404754 hasConceptScore W4285404754C104317684 @default.
• W4285404754 hasConceptScore W4285404754C110083411 @default.
• W4285404754 hasConceptScore W4285404754C11413529 @default.
• W4285404754 hasConceptScore W4285404754C115903097 @default.
• W4285404754 hasConceptScore W4285404754C119857082 @default.
• W4285404754 hasConceptScore W4285404754C12267149 @default.
• W4285404754 hasConceptScore W4285404754C154945302 @default.
• W4285404754 hasConceptScore W4285404754C169258074 @default.
• W4285404754 hasConceptScore W4285404754C185592680 @default.
• W4285404754 hasConceptScore W4285404754C206688291 @default.
• W4285404754 hasConceptScore W4285404754C2778403875 @default.
• W4285404754 hasConceptScore W4285404754C37736160 @default.
• W4285404754 hasConceptScore W4285404754C41008148 @default.
• W4285404754 hasConceptScore W4285404754C50644808 @default.
• W4285404754 hasConceptScore W4285404754C52001869 @default.
• W4285404754 hasConceptScore W4285404754C55493867 @default.
• W4285404754 hasConceptScore W4285404754C63479239 @default.
• W4285404754 hasLocation W42854047541 @default.
• W4285404754 hasOpenAccess W4285404754 @default.
• W4285404754 hasPrimaryLocation W42854047541 @default.
• W4285404754 hasRelatedWork W2086889680 @default.
• W4285404754 hasRelatedWork W2118190631 @default.
• W4285404754 hasRelatedWork W2119349310 @default.
• W4285404754 hasRelatedWork W2899532525 @default.
• W4285404754 hasRelatedWork W2997511728 @default.
• W4285404754 hasRelatedWork W3013617128 @default.
• W4285404754 hasRelatedWork W3153505674 @default.
• W4285404754 hasRelatedWork W4213079490 @default.
• W4285404754 hasRelatedWork W4246466849 @default.
• W4285404754 hasRelatedWork W4381745996 @default.
• W4285404754 hasVolume "208" @default.
• W4285404754 isParatext "false" @default.
• W4285404754 isRetracted "false" @default.
• W4285404754 workType "article" @default.