@Article{crph1224,
AUTHOR = {Sondinti, Lakshminarayana Reddy Kothapalli and Yasmeen, Zakera},
TITLE = {Analyzing Behavioral Trends in Credit Card Fraud Patterns: Leveraging Federated Learning and Privacy-Preserving Artificial Intelligence Frameworks},
JOURNAL = {Current Research in Public Health},
VOLUME = {2},
YEAR = {2022},
NUMBER = {1},
PAGES = {38-49},
URL = {https://www.scipublications.com/journal/index.php/UJBM/article/view/1224},
ISSN = {2831-5162},
DOI = {10.31586/ujbm.2022.1224},
ABSTRACT = {We investigate and analyze the trends and behaviors in credit card fraud attacks and transactions. First, we perform logical analysis to find hidden patterns and trends, then we leverage game-theoretical models to illustrate the potential strategies of both the attackers and defenders. Next, we demonstrate the strength of industry-scale, privacy-preserving artificial intelligence solutions by presenting the results from our recent exploratory study in this respect. Furthermore, we describe the intrinsic challenges in the context of developing reliable predictive models using more stringent protocols, and hence the need for sector-specific benchmark datasets, and provide potential solutions based on state-of-the-art privacy models. Finally, we conclude the paper by discussing future research lines on the topic, and also the possible real-life implications. The paper underscores the challenges in creating robust AI models for the banking sector. The results also showcase that privacy-preserving AI models can potentially augment sharing capabilities while mitigating liability issues of public-private sector partnerships [1].},
}

%0 Journal Article
%A Sondinti, Lakshminarayana Reddy Kothapalli
%A Yasmeen, Zakera
%D 2022
%J Current Research in Public Health

%@ 2831-5162
%V 2
%N 1
%P 38-49

%T Analyzing Behavioral Trends in Credit Card Fraud Patterns: Leveraging Federated Learning and Privacy-Preserving Artificial Intelligence Frameworks
%M doi:10.31586/ujbm.2022.1224
%U https://www.scipublications.com/journal/index.php/UJBM/article/view/1224

TY  - JOUR
AU  - Sondinti, Lakshminarayana Reddy Kothapalli
AU  - Yasmeen, Zakera
TI  - Analyzing Behavioral Trends in Credit Card Fraud Patterns: Leveraging Federated Learning and Privacy-Preserving Artificial Intelligence Frameworks
T2  - Current Research in Public Health
PY  - 2022
VL  - 2
IS  - 1
SN  - 2831-5162
SP  - 38
EP  - 49
UR  - https://www.scipublications.com/journal/index.php/UJBM/article/view/1224
AB  - We investigate and analyze the trends and behaviors in credit card fraud attacks and transactions. First, we perform logical analysis to find hidden patterns and trends, then we leverage game-theoretical models to illustrate the potential strategies of both the attackers and defenders. Next, we demonstrate the strength of industry-scale, privacy-preserving artificial intelligence solutions by presenting the results from our recent exploratory study in this respect. Furthermore, we describe the intrinsic challenges in the context of developing reliable predictive models using more stringent protocols, and hence the need for sector-specific benchmark datasets, and provide potential solutions based on state-of-the-art privacy models. Finally, we conclude the paper by discussing future research lines on the topic, and also the possible real-life implications. The paper underscores the challenges in creating robust AI models for the banking sector. The results also showcase that privacy-preserving AI models can potentially augment sharing capabilities while mitigating liability issues of public-private sector partnerships [1].
DO  - Analyzing Behavioral Trends in Credit Card Fraud Patterns: Leveraging Federated Learning and Privacy-Preserving Artificial Intelligence Frameworks
TI  - 10.31586/ujbm.2022.1224
ER  -