Digital Commons Network^™

Ai-Enabled Federated Learning System For Privacy-Preserving Health Insurance Underwriting And Fraud Detection, Vijayalaxmi Methuku

Defensive Publications Series

This disclosure presents an AI-powered federated learning system designed to enhance health insurance underwriting and fraud detection while maintaining strict privacy standards. The proposed system enables healthcare providers, insurers, and regulatory bodies to collaboratively train machine learning models without sharing sensitive patient data. The federated architecture ensures secure data processing, bias mitigation, and real-time fraud detection. Key innovations include distributed AI training, differential privacy, blockchain-based claim tracking, reinforcement learning for policy adjustments, and NLP-driven prior authorization automation. This system optimizes risk assessment, reduces fraudulent claims, and ensures transparency in health insurance operations.

Foreword, Madeleine "Mady" Clahane, Lissa L. Broome

North Carolina Banking Institute

No abstract provided.

Evaluating Campus Safety: Insights From Cal Poly Students, Demaree E. Lewis

Communication Studies

Campus safety is a major concern for students and faculty, especially in light of a few recent incidents at Cal Poly. This study explores students’ overall perceptions of safety, thoughts on Cal Poly’s method of communicating with students about crises, and the selection process of Resident Advisors (RA) on campus. Using a mixed methods approach, a survey collected responses from 125 students at Cal Poly, analyzing both qualitative and quantitative data. Analysis showed significant gender differences, with women reporting lower feelings of safety, satisfaction of Cal Poly crisis communication efforts, and overall lower trust in RA’s and Cal Poly’s vetting …

The Advice Of Counsel Defense: No Longer A Fraudster’S Shield, Maxwell Newman

North Carolina Banking Institute

No abstract provided.

Who Watches The Watchers?: Finra, Self-Regulatory Organizations, And The Next Evolution Of Appointment And Removal Jurisprudence, Hans M. Frank-Holzner

Minnesota Law Review Vols. 106:2 onward (2021-present)

There are private, non-profit corporations exercising significant executive power. Known as self-regulatory organizations (SROs) these non-governmental organizations make binding rules and sometimes enforce statutory law governing massive industries. One such SRO is the Financial Industry Regulatory Authority (FINRA). In 2022 alone, FINRA permanently barred 227 individuals and suspended 328 individuals from the financial industry, imposed $54.5 million dollars in fines, ordered $26.2 million dollars in restitution, and referred 663 cases for prosecution. FINRA’s regulatory jurisdiction is massive. In 2022, it oversaw 3,378 securities firms including 150,647 branch offices and 620,882 individuals nationwide. This immense power is wielded not by the …

Deepfake Image Detection Using Explainable Ai And Deep Learning, Abdallah Abdulfattah Mohammed Abdulrahman

Theses

Deepfake technology has grown exponentially, and it has changed our perspective of managing digital content. The technology has many applications, but its ease of access has brought many risks. These risks include identity theft, misinformation spread, development of non-consensual content, and a decrease in trust in media. To address these challenges, we propose a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for deepfake image detection. We developed a CNN model and four hybrid CNN-LSTM models in our study. Our approach integrates the strengths of CNNs for spatial feature extraction and LSTMs for …

Retail Investors And Investment Fraud Victims: Is There A Connection?, Jason Martin

Staff Scholarship

This study analyzed specific characteristics of investment fraud victims. Logistic regressions on a national sample of retail investors revealed that overconfident and financially literate investors shared several characteristics with victims of investment fraud. While overconfident investors were the most comfortable with market regulation and making investment decisions that assumed high amounts of risk relative to investment returns, financially literate investors surpassed them in the frequency of annual trading and portfolio allocation to stocks. Surprisingly, overconfident investors favored due diligence via background checks on investment professionals, while financially literate investors did not. Overall, males and younger investors tended to share characteristics …

Educating Students On The Behavioral And Psychological Aspects Of Romance Scam Victimization Via A Social Engineering Competition, Rachel Bleiman, Hwanhee Park, Aunshul Rege

Journal of Cybersecurity Education, Research and Practice

The online dating industry generated 2.98 billion USD in 2023 and is estimated to reach 3.6 billion USD by 2025. Not surprisingly, online dating platforms are rife with romance scams that cause financial damages, with estimated losses of 1.3 billion USD in 2022 alone. Additionally, victims suffer emotional and psychological harms. This paper shares findings from a 2023 Romance Scam and Social Engineering Competition (RSSEC) that introduced students to the behavioral and psychological aspects of romance scams. Specifically, the competition aimed to expose students to (i) understanding how victims experience social engineering (SE) - the psychological manipulation of human behavior, …

Email Spam Classification Based On Deep Learning Methods: A Review, Ekramul Haque Tusher, Mohd Arfian Ismail, Anis Farihan Mat Raffei

Iraqi Journal for Computer Science and Mathematics

Email spam is a significant issue confronting both email consumers and providers. The evolution of spam filtering has progressed considerably, transitioning from basic rule-based filters to more sophisticated machine learning algorithms. Deep learning has become a potent collection of techniques for addressing intricate issues such as spam classification in recent times. A thorough literature evaluation is required to have a comprehensive overview of the current research on utilizing deep learning methods for email spam classification. This review aims to identify the various deep learning techniques used for email spam, their effectiveness, and areas for future research. By synthesizing the outcomes …

The Ethical Governance Of Artificial Intelligence: Using The Ai Integrative Risk-Based (Airb) Model To Achieve Compliance Risk Management, Miriam Weismann

University of Miami Business Law Review

While undeniably powerful, artificial intelligence algorithms also pose significant risks. The ethical, legal, social, and scientific implications of various AI models can be profound, as demonstrated by the subprime mortgage crisis. This crisis, worsened by the unregulated use of derivative algorithms, is a stark reminder of the pivotal role of individual accountability, ethical responsibility, and regulation in preventing future “catastrophic harm.”1 This Article ventures into the uncharted territory of AI ethical governance and aims to advance AI scholarship and address the unresolved issue of ethical compliance management in AI. Employing a risk-based assessment tool is critical for developing regulatory and …

Anogat-Sparse-Tl: A Hybrid Framework Combining Sparsification And Graph Attention For Anomaly Detection In Attributed Networks Using The Optimized Loss Function Incorporating The Twersky Loss For Improved Robustness., Nadhem Ebrahim, Wasim Khan

University Research

In recent years, the identification of abnormalities in attributed networks has become essential for applications including social media analysis, cybersecurity, and financial fraud detection. Unsupervised graph anomaly detection techniques seek to recognize infrequent and anomalous patterns in graph-structured data without the necessity of labelled instances. Conventional methods employing Graph Neural Networks (GNNs) frequently encounter difficulties, especially due to the transmission of noisy edges and the intrinsic intricacy of node interrelations. To overcome these restrictions, we introduce ANOGAT-Sparse-TL, an innovative hybrid framework that integrates graph sparsification and Graph Attention Networks (GAT) with autoencoder-based reconstruction for anomaly detection in attributed networks. The …

Insider Risks And The Evolving Role Of Executive Protection Professionals In Cybersecurity, Alan Saquella

Publications

Insider risks have long been a critical concern in corporate security, traditionally encompassing threats from employees, contractors, or third-party vendors with access to sensitive information. However, as digital transformation accelerates, the convergence of physical and cyber threats has created new vulnerabilities. Executive protection (EP) professionals, historically tasked with safeguarding high-profile individuals from physical threats, now find themselves on the frontlines of combating cyber-criminal attacks. Expanding their skill sets to include cybersecurity awareness is no longer optional—it is a necessity.

This article explores insider risks, the growing need for executive protection professionals to adapt, and practical ways they can enhance their …

Investor Justice, Nicole Iannarone

Minnesota Law Review Vols. 106:2 onward (2021-present)

There is a systemic flaw in the investor protection landscape. Unrepresented investors face off against well-resourced repeat- player firms that almost always have lawyers. While consumers face similar challenges in civil courts, in forced securities arbitration, the decisionmaker may not have a law degree, is prohibited from conducting any outside legal research, and has no monetary incentive to read materials the parties submit. These realities amplify already-existing informational and resource asymmetries between Main Street investors and stockbrokers and undermine the market-legitimizing function of securities arbitration. Despite being designed to permit investors to recoup losses without the aid of an attorney, …

Deepfakes Can Ruin Lives And Livelihoods – Would Owning The ‘Rights’ To Our Own Faces And Voices Help?, Graeme W. Austin, Jane C. Ginsburg

Faculty Scholarship

Not that long ago, the term “deepfake” wasn’t in most people’s vocabularies. Now, it is not only commonplace, but is also the focus of intense legal scrutiny around the world.

Known in legal documents as “digital replicas”, deepfakes are created by artificial intelligence (AI) to simulate the visual and vocal appearance of real people, living or dead.

Unregulated, they can do a lot of damage, including financial fraud (already a problem in New Zealand), political disinformation, fake news, and the creation and dissemination of AI-generated pornography and child sexual abuse material.

For professional performers and entertainers, the proliferation and increasing …

Legal Gaps In Personal Data Protection: Reforming Indonesia’S Population Administration Law, Ninuk Triyanti, I Gusti Ayu Ketut Rachmi Handayani, Lego Karjoko

Hasanuddin Law Review

This study critically examines the existing legal framework for personal data protection within Indonesia’s population administration system. Through a normative legal research approach, it identifies significant regulatory gaps that leave personal information vulnerable to misuse and breaches. The results show that the current legal policies remain insufficient, as numerous aspects of personal data protection have yet to be explicitly regulated in the Population Administration Law. Despite the enactment of a national personal data protection law, its effectiveness is undermined by the lack of comprehensive integration into the Population Administration Law. This research proposes reconstructing the legal framework to address essential …

Good Faith In Life Insurance Contract By Indonesian Court, Mokhamad Khoirul Huda

Hasanuddin Law Review

This paper reviews both the interpretation of good faith and its implementation by the Court in terms of life insurance contracts. The principle of good faith in life insurance contracts was under the provision of the Article 251 Wet Boek van Kophandel which assigned the obligation of good faith on the insured. Based on the context of its historical and systematical interpretation, the obligation of good faith should be on both sides, the insurer and the insured. The insured had an obligation to inform any material facts and the insurer had to investigate those all facts. Until recent days, however, …

Legal Status Of Cryptocurrency Circulation In Iraq: Lessons From The United Arab Emirates And The United States, Ghassan Adhab Atiyah, Nazura Abdul Manap, Saidatul Nadia Abd Aziz

Hasanuddin Law Review

The philosophical emergence of cryptocurrencies is a consequence of the desire to get rid of the authorities’ control of the monetary system, which encouraged people to deal with it for investment or to facilitate the fulfilment of their financial obligations. The research problem is represented through the lack of legislation that regulates dealing with cryptocurrencies in Iraq. There are many technical, legal, and security risks for the use and circulation of cryptocurrency, which must be legally addressed and suitable solutions found. Therefore, this article aims to examine and analyse the legal status of cryptocurrencies in selected jurisdictions through multiple stages, …

Security And Privacy Risks Of Multiple Payment Systems, Miguel Silva

Defensive Publications Series

The proliferation of multiple payment systems has introduced significant security and privacy risks, as users navigate a complex landscape of digital transactions. These risks arise from vulnerabilities in system integration, data breaches, and insufficient encryption protocols. Additionally, the lack of standardized security practices across platforms exacerbates the challenges of ensuring user privacy. Addressing these concerns requires comprehensive solutions that prioritize robust encryption, secure data sharing, and unified regulatory frameworks.

Domesticating Foreign Finance, Jeremy C. Kress

Florida Law Review

More than a decade after the 2008 financial crisis, U.S. policymakers still have not adequately addressed one of the primary causes of the crash: foreign banks. When foreign banks first entered the United States fifty years ago, they specialized in traditional banking products like loans and deposit accounts. Over time, however, many foreign banks shifted to a riskier strategy focused on speculative capital markets investments and fueled by volatile short-term debt. This novel business model created vulnerabilities for the U.S. financial system, as became clear when Deutsche Bank, Barclays, UBS, and other foreign banks accelerated the 2008 crisis. This Article …

The Impact Of Carbon Disclosure On Firm Value: Examining The Role Of Institutional Ownership In The Energy Sector, Hendra Arie Rachmadhika, Amrie Firmansyah

Journal of Accounting Auditing and Business

This study examines the influence of carbon disclosure on firm value with institutional ownership as a moderator in energy sector companies listed on the Indonesia Stock Exchange during 2019-2022. Carbon disclosure is measured using the disclosure scale developed by Bae Choi et al. (2013a), the percentage of institutional ownership in the company to calculate institutional ownership, and Tobin's Q to calculate firm value. This study uses data from energy sector companies listed on the Indonesia Stock Exchange for the observation period of 2019-2022, with a total of 80 observations through purposive sampling. The results show that carbon disclosure has a …

Do You Know How To Prevent Financial Fraud In Your Dental Practice?, Phil Nieto

Virginia Dental Journal

Financial fraud is a significant concern for dental practices, with an estimated 20%-60% of dentists affected over their careers. To prevent embezzlement, dentists should utilize the security functions of their practice management software, including setting high-level user permissions and audit logs. Daily checks on patient returns and weekly audits of financial consistency are crucial. Monitoring these areas can help detect and deter fraudulent activities, ensuring the financial health of the practice.

Deficiencies In The Judicial Classification Of Cryptocurrencies Indicating The Need For Legislative Alternatives, Ethan Johnson

Journal of Legislation

The cryptocurrency industry is desperate for regulatory clarification, which would stabilize and secure cryptocurrency and, ultimately, promote increased investment. How the United States ultimately chooses to pursue cryptocurrency regulation has massive implications for future investment and the development of this technology. Disagreement over how to classify cryptocurrency under the investment contract test created in SEC v. Howey, including the recent Second Circuit split, has led to calls for resolving legislation. Cryptocurrency legislation has recently been passed by the European Union, and there are currently proposals for legislation before Congress in the United States.

This Note considers the context surrounding …

The Role Of Advanced Business Analytics In Shaping Organizational Decision-Making In Banking Industry, Krystal S. Mcdowall

Theses and Dissertations

This study explores the role of advanced business analytics in shaping decision-making within the banking industry, focusing on its implementation, impact, and the challenges that financial institutions face. As banks increasingly embrace data-driven strategies to enhance competitiveness and customer service, analytics has emerged as a key enabler of operational efficiency and strategic foresight. However, despite its potential, banks often encounter obstacles such as legacy systems, data silos, regulatory constraints, and skill shortages that hinder full-scale integration. Adopting a mixed-methods research design, the study combines quantitative survey data from banking professionals with qualitative insights drawn from interviews and secondary data analysis …

Online Dating Experiences And Body Dissatisfaction Among Transgender And Gender Nonconforming Individuals: A Qualitative Study, Luciano Caprio M.S.

Selected Full Text Dissertations, 2011-

Through the evolution of online dating applications, individuals are able to form interpersonal connections with one another at a rapid pace. The effects of such communications can hold both protective and risk factors within the LGBTQ+ community. Previous research suggests that lesbians, gay, and bisexuals who have experienced weight discrimination, particularly fatphobic and anti-fat attitudes, while utilizing these online dating platforms, have increased body dissatisfaction. However, there is minimal research focusing on the implications of discrimination, body dissatisfaction, and the usage of online dating platforms in the transgender and gender nonconforming (TGNC) community. This qualitative study explored the experiences of …

Persistence Is Not Key: A Study On The Relationship Between The Persistence Of Going Concern Opinion Type I Errors And Investor Confidence, Christin Marie Kooti

Theses, Dissertations and Capstones

This study examines how persistent Type I errors in going concern opinions impact investors’ decisions and confidence in the warning signal embedded in the opinion. Despite regulatory changes intended to improve audit accuracy and restore investors’ confidence in the audit profession, such as the Sarbanes-Oxley Act and the Accounting Standard Update 14-15, along with the StoneRidge Investment Partners vs. Scientific Atlanta Court Case verdict, persistent going concern opinions (Type I errors) weaken the perceived informativeness of audit warnings. Signaling theory provides the framework to explore the question: “Do persistent Type I errors in going concern opinions influence investors’ perceptions of …

Predicting Price Movements Of The S&P 500 Using Conventional And Alternative Market Indicators, Patrick M. Scarborough

Theses and Dissertations

This thesis investigates whether integrating alternative data sources with conventional financial indicators enhances S&P 500 forecasting accuracy in modern financial markets characterized by increased complexity and rapid information flows. The study analyzes daily S&P 500 returns using twelve predictor variables comprising conventional indicators (VIX volatility index, WTI crude oil, gold futures, AAA bond yields, Federal Funds Rate, Treasury yield spreads) and alternative data sources (Bitcoin returns, Daily News Sentiment Index, Indeed job postings, Economic Policy Uncertainty Index) across 1,341 observations from February 2020 to June 2025. The methodology employs ordinary least squares regression and ARIMAX(5,5) modeling with rigorous preprocessing including …

Gleeson Library Ai Taskforce Final Report, Anders Lyon, Amanda Raver, Kristie Barlas, Shawn P. Calhoun, Annie Pho, Brian Schumacher, Claire Sharifi, Gina Solares

Gleeson Library Initiatives

During the Fall 2025 semester, the Gleeson Library AI Taskforce examined how artificial intelligence is influencing higher education and what those changes mean for library work at USF. By reviewing AI activity across campus, surveying library staff, and analyzing how Jesuit institutions are responding to AI, the Taskforce found a landscape that is evolving quickly but thoughtfully. Across these contexts, interest in AI literacy is growing, experimentation with new tools is expanding, and there is a clear need for library-specific guidance, particularly given that no Association of Jesuit Colleges and Universities (AJCU) libraries have published AI policies or frameworks of …

Scalable Approaches Towards Characterizing And Mitigating Emerging Phishing Scams, Sayak Saha Roy

Computer Science and Engineering Dissertations - Archive

Phishing scams are among the most dangerous and persistent forms of cybercrime, leveraging social engineering to exploit human behavior and obtain sensitive information, leading to widespread identity theft and data breaches. In the past year, these attacks have resulted in financial losses exceeding $10 billion in the United States alone. As phishing scams continue to evolve, they have not only expanded in scale but also grown in sophistication, spreading rapidly across social media and employing adversarial techniques to evade detection by anti-scam tools. The situation is further exacerbated by the availability of advanced phishing kits, and more recently, generative AI, …

Ai And Strategic Power: An Analysis Of Ai In Cyberwarfare, Krystal J. Correal

Senior Honors Theses and Projects

Artificial intelligence (AI) is intertwined in nearly all aspects of civilian life and is becoming progressively embedded into global conflict in novel ways. AI’s role in cyberwarfare is altering the structure of strategic power. This paper explores how the weaponized application of AI in cyberwarfare, both in military and public use, work to benefit states with advanced AI capabilities in kinetic and non-kinetic forms while undermining those without. With the focus on superpowered states, such as the U.S., China, and Russia, and a representative non-superpower, Ukraine, the study examines the basic requirements for AI dominance: resources (financial and other), technological …

Regulatory Personhood: The Elixir For Redundancy Between The Sec And The Pcaob, Sarah Williams

Faculty Scholarly Works

The Public Company Accounting Oversight Board (“PCAOB” or “Board”) is a quasi-governmental regulatory agency created by Congress in 2002 in response to revelations of widespread financial fraud at major public companies. Since its creation, the agency has experienced significant challenges. Litigants have challenged its constitutionality, the Trump administration challenged its very existence, and legislation was introduced in 2021 to transfer its responsibilities to the U.S. Securities and Exchange Commission (“SEC”).

Proposals to eradicate the Board asserted vague concerns about the redundancy of its responsibilities with those of the SEC, and alleged resultant monetary waste. This Article, written in 2022, provides …