Technology-Enhanced Student Success Program Short Report

Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities

Large language models (LLMs), and generative AI generally, raise significant concerns regarding human rights. Their promise in finding insights in patterns of data have to be weighed against potential risks to individuals and societies. The typical perspective, which emphasizes accuracy, capability, or scope of such systems, overlooks the fact that generative AI technologies exploit massive collections of data about human behaviors, thoughts, and ideas. The datafication of human life should be examined through the lens of human rights, specifically with regard to autonomy, dignity, equality, and community. This piece argues that discussions about LLMs and generative AI are inherently linked to data originated from individuals, whose information are embedded in the training data. Data are human rights issues because information about individuals are buried in the data. Technical solutions alone are insufficient to address the human rights distortions produced by LLMs. Policy should focus instead on the fact that data are collected on rights-bearing individuals and groups who have been given very little leeway to discuss the implications of or choose to be in the enterprise of creating generative AI.

This project focuses on leveraging generative AI to analyse user reviews from the Play Store for diverse applications. By utilizing advanced large language models (LLMs), the system processes extensive user feedback to identify key trends, sentiments, and actionable insights. The AI analyses reviews to categorize overall user sentiment (positive, negative, or neutral), highlight recurring issues, and identify popular feature requests. The generative AI’s capabilities enable it to provide nuanced suggestions to developers, such as improving app functionality, addressing common complaints, and implementing features aligned with user preferences. Additionally, the system can generate concise summaries of user reactions, offering developers a clear understanding of their app's strengths and areas needing improvement. This data-driven approach enhances app development by prioritizing updates based on real user needs, improving user satisfaction, and fostering higher ratings on the Play Store. The integration of generative AI streamlines the review analysis process, ensuring actionable recommendations for sustained app success. Key Words: Generative AI, Large Language Models (LLMs), sentiment analysis, App improvement, review analysis 1.INTRODUCTION This project utilizes generative AI to analyze Play Store reviews across various applications, providing developers with actionable insights. By leveraging large language models (LLMs), the system processes user feedback to identify sentiment trends, highlight common issues, and suggest improvements. This approach enables developers to understand user reactions effectively and prioritize updates, ultimately enhancing app quality, user satisfaction, and ratings. The integration of AI streamlines review analysis, ensuring data-driven decisions for better app performance.

The emergence of generative AI (GenAI) is a major driving force behind the modern data science ecosystem, a field that exploits data as the central asset for actionable insights. Analogously, GenAI is a form of artificial intelligence which learns from massive datasets to generate new data, showcasing human-like creativity in text, images to code, speech, and video. Two critical pillars of the GenAI technology are large language models (LLMs) and vector data. In particular, LLMs are a category of genAI models that emphasize on generating new text contents. On the other hand, there is also an upsurge of dense, high-dimensional, billion-scale vector data from deep learning models that embed complex data, e.g., text, multimedia, graphs, and tables into vector representations aiming to preserve semantic similarity. Since LLMs operate on vector data at various stages consisting of pre-training, fine-tuning, inference, and retrieval-augmented generation (RAG), coupling large language models with vector data management is essential for enhancing data science services with cross-modal data querying and generation. It creates new opportunities and challenges in areas such as accuracy, consistency, efficiency, scalability, privacy, fairness, explainability, data regulations, software-hardware collaboration, and cloud-native systems. The workshop aims to advance the understanding of how LLMs and vector data management can cooperatively contribute to data science solutions.

BackgroundNIAGADS is a national data repository that offers qualified investigators access to genomic data for Alzheimer’s disease (AD) and related dementia. In addition, NIAGADS has made substantial effort to curate, harmonize, standardize, and disseminate AD‐relevant variant, gene, and sequence annotations from publications, functional genomics datasets, and summary statistics deposited at NIAGADS. These results are made available to the public in a collection of interactive knowledgebases (AD Variant Portal, FILER Functional Genomics Repository, VariXam, Alzheimer’s GenomicsDB & Genome Browser), all of which are accessible programmatically via the NIAGADS API. However, as these offerings grow, navigating them can be challenging. Here, we introduce AI‐based enhancements to NIAGADS sites to help guide researchers and facilitate data discovery.MethodWe leverage OpenAI’s generative AI to build and train three large language models (LLMs) based on NIAGADS documentation, step‐by‐step recipes for data‐access requests, subject‐specific vocabularies, and the OpenAPI specification defining the NIAGADS API that allows programmatic access to the NIAGADS knowledgebases. For users of the API and to enhance search interfaces, we build on the LLMs to construct a framework for handling complex natural language instructions that decomposes an inquiry into tasks and subtasks and then plans, selects, and optionally executes API calls and parses the results.ResultDeveloping these LLMs allows NIAGADS to improve user experiences by integrating topic‐specific chatbots and generative AI search tools into NIAGADS sites. Rule‐based chatbots that leverage conversational AI on the NIAGADS portal and Data Sharing Service will respond to inquiries with answers inferred from the LLMs, with responses improving with user feedback. These bots will also supplement help requests, suggesting solutions to common inquiries. Planner‐enhanced generative AI based on the API‐specification trained LLMs will be tied to knowledgebase searches and filters in resources such as the GenomicsDB and FILER to allow users to leverage natural language processing to ask sophisticated questions that require multiple API calls to resolve the answer.ConclusionIntroducing AI‐enhanced search creates an interactive opportunity for NIAGADS users to learn new information or discover resources and tools they can use to supplement their research, which, in turn, improves NIAGADS ability to support AD genetics research.

Distribution network design is one of the most essential strategic decisions in logistics systems and supply chains, as it structures the network by determining the number of echelons and specifying the types, quantities, and locations of various facilities. This chapter presents decision-support models for distribution and logistics network design, covering both continuous location models (gravity location models) and discrete network design models (capacitated/uncapacitated and their relevant variants). Comprehensive numerical experiments based on the same case study offer a direct comparison of these different network design approaches. Furthermore, as one of the most disruptive technologies in Industry 5.0, the impact of generative AI (GenAI) and large language models (LLMs) on the research and education of distribution network design is thoroughly analyzed. Our experiments demonstrate that GenAI and LLMs are powerful tools in providing structured introductions to existing problems, guiding model selection and explanation, assisting with coding and code clarification, facilitating model comparison, and generating initial ideas for new research questions in distribution and logistics network design. However, they also face reliability and accuracy challenges, exhibit limited critical thinking capabilities, and struggle to address emerging research questions. Our findings offer valuable guidance for incorporating GenAI tools and LLMs into research and educational processes in distribution and logistics network design.

This paper presents a comprehensive survey of the applications, challenges, and limitations of Generative AI (GenAI) in enhancing threat intelligence within cybersecurity, supported by real-world case studies. We examine a wide range of data sources in Cyber Threat Intelligence (CTI), including security reports, blogs, social media, network traffic, malware samples, dark web data, and threat intelligence platforms (TIPs). This survey provides a full reference for integrating GenAI into CTI. We discuss various GenAI models such as Large Language Models (LLMs) and Deep Generative Models (DGMs) like Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Diffusion Models, explaining their roles in detecting and addressing complex cyber threats. The survey highlights key applications in areas such as malware detection, network traffic analysis, phishing detection, threat actor attribution, and social engineering defense. We also explore critical challenges in deploying GenAI, including data privacy, security concerns, and the need for interpretable and transparent models. As regulations like the European Commission’s AI Act emerge, ensuring trustworthy AI solutions is becoming more crucial. Real-world case studies, such as the impact of the WannaCry ransomware, the rise of deepfakes, and AI-driven social engineering, demonstrate both the potential and current limitations of GenAI in CTI. Our goal is to provide foundational insights and strategic direction for advancing GenAI’s role in future cybersecurity frameworks, emphasizing the importance of innovation, adaptability, and ongoing learning to enhance resilience against evolving cyber threats. Ultimately, this survey offers critical insights into how GenAI can shape the future of cybersecurity by addressing key challenges and providing actionable guidance for effective implementation.

Generative AI (GenAI), exemplified by Large Language Models (LLMs), such as OpenAI’s ChatGPT, is revolutionizing various fields. Central to this transformation is Data Center Networking (DCN), which not only provides the infrastructure support for GenAI operation, but also provisions GenAI services to users. Hence, this article explores the interplay between GenAI and DCNs, analyzing their symbiotic relationship and mutual advances. We begin by reviewing the current challenges of DCNs and GenAI-based solutions, such as data augmentation, process automation, and domain transfer. We then discuss the distinctive characteristics of GenAI workloads on DCNs, gaining insights that catalyze the evolution of DCNs to more effectively support GenAI. Moreover, to illustrate the seamless integration of GenAI with DCNs, we present a case study on GenAI-empowered DCN digital twins. Specifically, we employ an LLM equipped with retrieval augmented generation to formulate optimization problems for DCNs (e.g., resource allocation and routing) and adopt diffusion-deep reinforcement learning to solve optimization. The experimental results on a representative DCN optimization problem, i.e., knowledge placement, demonstrate the validity and efficiency of our proposals. We anticipate that this article can promote further research to enhance the virtuous interaction between GenAI and DCNs.

Burnout has become a significant concern in high-stress industries, impacting mental health and productivity. Traditional burnout management solutions lack real-time adaptability and personalized intervention strategies. This research explores an AI-driven burnout management mechanism leveraging Generative AI, MongoDB Atlas, Python, and Large Language Models (LLMs) to provide real-time detection, personalized coping strategies, and predictive analytics. The system collects and stores user responses, behavioral patterns, and sentiment data in MongoDB Atlas, while LLMs analyze and generate tailored burnout mitigation recommendations. Experimental results demonstrate the effectiveness of the proposed approach in early burnout detection, personalized intervention, and user engagement, showing improvements in stress reduction and work-life balance. The proof of concept for AI-powered burnout detection and intervention demonstrates the technical feasibility of using Large Language Models (LLMs), Generative AI, MongoDB Atlas, and Python-based automation for real-time mental health support. The system successfully classifies burnout severity using LLMs trained on sentiment analysis, achieving an accuracy of 91.2%, which significantly outperforms traditional rule-based sentiment models. The use of MongoDB Atlas for scalable data storage ensures real-time burnout tracking, while FastAPI-based backend automation allows for seamless integration across platforms. Furthermore, Generative AI provides personalized stress interventions, dynamically adapting to user feedback and improving engagement. These technical validations highlight how AI-driven burnout management can be scalable, real-time, and enterprise-ready, paving the way for AI-powered diagnostics in mental health applications across various industries.

This article examines the application of Large Language Models (LLM) – GPT-4, Claude, Cohere, and Llama – to assess students’ open-ended responses in Geography exams. The models’ assessment scores were compared to assessment and scores by the original multi-stage human assessment as well as two additional human expert scoring. The case study considers the high-stakes national matriculation exam in Finland. The exam results play a crucial role in determining individuals’ eligibility for higher education, including a study right in Geography at the university. We selected 18 essays that had originally been given 5 (basic), 10 (good) and 15 (excellent) points on a scale from 0 to 15 points. Findings show variability between LLMs and notable differences between LLM and human evaluations. The language of responses and grading instruction influenced LLM performance. These results highlight the potential and complexities of integrating generative AI today in learning assessments to score open-ended responses. Precise control of prompts and LLM settings proved crucial for the LLM to align with original assessment scores more closely.

The integration of Large Language Models (LLMs) into radiological practice offers promising opportunities to support reporting, workflow optimization, and clinical decision-making. To provide an exemplary demonstration of an LLM's self-reflection on the use of LLMs in radiology and acritical evaluation of their possibilities and limitations. In this article, an LLM (Claude AI, Version3.5 Sonnet AI Assistant, Anthropic, PBC) reflects on its own potential and limitations within the context of radiological practice. Claude was iteratively employed to analyze and systematically present relevant topics. The utilized LLM demonstrates remarkable capabilities in generating structured content and identifying radiological applications. LLMs offer promising support but need to be used responsibly for radiological applications. LLMs such as Claude are powerful tools whose effectiveness depends on the user's ability to critically assess the generated content. Addressing ethical and practical challenges is essential to ensure abalance between technological assistance and medical autonomy. Future developments in generative AI, including potential singularity scenarios, require thoughtful and responsible application to maximize clinical benefits and minimize risks.

The emergence of large language models (LLMs) has ushered in a new era of generative AI, exhibiting broad human-level capabilities and achieving meaningful progress toward Artificial General Intelligence (AGI). To realize AGI that truly benefits each individual, one next key direction for generative AI is to develop personal intelligence -understanding individuals and enhancing personal thinking, planning, and life experiences through personalization. Although evolving generative AI toward personal intelligence is emerging, it has attracted considerable interest from both research institutions and industry, even becoming a strategic direction for many companies. This workshop aims to provide a platform for discussing innovative ideas that facilitate personal intelligence with generative AI, 1) envisioning the future of personal intelligence powered by generative AI, 2) item establishing benchmarks for personal intelligence tasks, 3) advancing user modeling/personalization techniques for generative models/agents, 4) enhancing real-world applications, and 4) ensuring privacy and trustworthiness. This workshop aims to deepen understanding, accelerate progress, and support the transformative development of personal intelligence. The website for the workshop is: https://generative-rec.github.io/workshop-www25.

Large Language Models (LLMs) have demonstrated remarkable performance across various downstream tasks, as evidenced by numerous studies. Since 2022, generative AI has shown significant potential in diverse application domains, including gaming, film and television, media, and finance. By 2023, the global AI-generated content (AIGC) industry had attracted over $26 billion in investment. As LLMs become increasingly prevalent, prompt engineering has emerged as a key research area to enhance user-AI interactions and improve LLM performance. The prompt, which serves as the input instruction for the LLM, is closely linked to the model’s responses. Prompt engineering refines the content and structure of prompts, thereby enhancing the performance of LLMs without changing the underlying model parameters. Despite significant advancements in prompt engineering, a comprehensive and systematic summary of existing techniques and their practical applications remains absent. To fill this gap, we investigate existing techniques and applications of prompt engineering. We conduct a thorough review and propose a novel taxonomy that provides a foundational framework for prompt construction. This taxonomy categorizes prompt engineering into four distinct aspects: profile and instruction, knowledge, reasoning and planning, and reliability. By providing a structured framework for understanding its various dimensions, we aim to facilitate the systematic design of prompts. Furthermore, we summarize existing prompt engineering techniques and explore the applications of LLMs across various domains, highlighting their interrelation with prompt engineering strategies. This survey underscores the progress of prompt engineering and its critical role in advancing AI applications, ultimately aiming to provide a systematic reference for future research and applications.

Generative AI systems based on Large Language Models (LLMs) have demonstrated remarkable capabilities in software engineering tasks, from code generation to natural language processing. However, a significant gap persists between curated demonstrations and production-grade deployment. This technical report presents a practitioner-driven analysis of LLM limitations encountered during sustained, real-world use across software development workflows. Drawing from multiple case studies—including natural-language-driven development (“vibe coding”), API integration, multi-file refactoring, and general-purpose question answering—we identify and taxonomize four critical failure modes: (1) the Complexity Cliff, where LLM performance degrades non-linearly as task interdependency grows; (2) Context Window Blindness, where finite attention spans cause silent contract violations across distributed codebases; (3) the Memory Illusion, where session discontinuity erases accumulated architectural knowledge; and (4) Confident Hallucination, where models generate plausible but fabricated outputs indistinguishable in tone from correct ones. We formalize the Verification Paradox—an inverse relationship between a user’s need for AI assistance and their capacity to validate its outputs—and propose a practical five-strategy framework for effective human–AI collaboration in software engineering contexts. We further introduce the concept of Contextual Reasoning Failure, evidenced by cases where LLMs optimize for literal query patterns while ignoring situational logic obvious to any human observer. Our findings suggest that current LLMs, while powerful pattern-matching engines, lack the contextual reasoning, persistent memory, and epistemic self-awareness necessary for reliable autonomous operation, and that practitioner expertise remains the critical safeguard against AI-induced defects in production systems.

Challenges such as hallucination and non-determinism are well known to undermine the reliability of Generative AI (GenAI) applications. Despite this, their use across multiple fields and domains continues to rapidly grow. Many GenAI applications now generate or interact with geospatial information – leading to the potential proliferation of non-human generated geospatial data. Because such tools can be developed without specialist geographic expertise, there is a growing risk of diminished oversight and declining geospatial data quality. This paper presents an approach for evaluating the geospatial information produced by large language models (LLMs) using established frameworks for geospatial data quality. We apply this framework in two experiments that assess the completeness, accuracy, precision, and consistency of LLM outputs: geoparsing and route finding. Interpreting these results through ontological and teleological perspectives reveals fundamental limitations in how LLMs represent and reason about space. The study highlights the need for responsible evaluation and adaptation of data quality standards as GenAI becomes increasingly embedded within geographic information science.