Byunggu Yu

Tailon D. Jackson, Byunggu Yu

This thesis investigates whether large language models (LLMs) can be guided to simulate a consistent personality through prompt engineering. The study explores this concept within the context of a chatbot designed for Speech-Language Pathology (SLP) student training, specifically focused on gender-affirming voice therapy. The chatbot, named Monae Jackson, was created to represent a 32-year-old transgender woman and engage in conversations simulating client-therapist interactions. Findings suggest that with prompt engineering, the chatbot maintained a recognizable and consistent persona and had a distinct personality based on the Big Five Personality test. These results support the idea that prompt engineering can be used to simulate stable personality characteristics in AI chatbots.

Veronica Wendt, Byunggu Yu, Caleb Kelly et al.

Self-attention transformers have demonstrated accuracy for image classification with smaller data sets. However, a limitation is that tests to-date are based upon single class image detection with known representation of image populations. For instances where the input image classes may be greater than one and test sets that lack full information on representation of image populations, accuracy calculations must adapt. The Receiver Operating Characteristic (ROC) accuracy thresh-old can address the instances of multi-class input images. However, this approach is unsuitable in instances where image population representation is unknown. We consider calculating accuracy using the knee method to determine threshold values on an ad-hoc basis. Results of ROC curve and knee thresholds for a multi-class data set, created from CIFAR-10 images, are discussed for multi-class image detection.

Byunggu Yu, Junwhan Kim

In order to detect unknown intrusions and runtime errors of computer programs, the cyber-security community has developed various detection techniques. Anomaly detection is an approach that is designed to profile the normal runtime behavior of computer programs in order to detect intrusions and errors as anomalous deviations from the observed normal. However, normal but unobserved behavior can trigger false positives. This limitation has significantly decreased the practical viability of anomaly detection techniques. Reported approaches to this limitation span a simple alert threshold definition to distribution models for approximating all normal behavior based on the limited observation. However, each assumption or approximation poses the potential for even greater false positive rates. This paper presents our study on how to explain the presence of anomalies using a neural network, particularly Long Short-Term Memory, independent of actual data distributions. We present and compare three anomaly detection models, and report on our experience running different types of attacks on an Apache Hypertext Transfer Protocol server. We performed a comparative study, focusing on each model's ability to detect the onset of each attack while avoiding false positives resulting from unknown normal behavior. Our best-performing model detected the true onset of every attack with zero false positives.

Kihoon Jang, Junwhan Kim, Byunggu Yu

In subscription-based businesses, the churn rate refers to the percentage of customers who discontinue their subscriptions within a given time period. Particularly, in the mobile games industry, the churn rate is often pronounced due to the high competition and cost in customer acquisition; therefore, the process of minimizing the churn rate is crucial. This needs churn prediction, predicting users who will be churning within a given time period. Accurate churn prediction can enable the businesses to devise and engage strategic remediations to maintain a low churn rate. The paper presents our highly accurate churn prediction method. We designed this method to take into account each individual user's distinct usage period in churn prediction. As presented in the paper, this approach was able to achieve 96.6% churn prediction accuracy on a real game business. In addition, the paper shows that other existing churn prediction algorithms are improved in prediction accuracy when this method is applied.