1 citations · 2 across the 5 of their papers we have counts for
5 papers
The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection
Jaturong Kongmanee, Smile Thanapattheerakul
This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confiden…
Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models
Jaturong Kongmanee
This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the m…
The Model Mastery Lifecycle: A Framework for Designing Human-AI Interaction
Mark Chignell, Mu-Huan Miles Chung, Jaturong Kongmanee +2
The utilization of AI in an increasing number of fields is the latest iteration of a long process, where machines and systems have been replacing humans, or changing the roles that…
Maximizing Information Gain in Privacy-Aware Active Learning of Email Anomalies
Mu-Huan Miles Chung, Sharon Li, Jaturong Kongmanee +7
Redacted emails satisfy most privacy requirements but they make it more difficult to detect anomalous emails that may be indicative of data exfiltration. In this paper we develop a…
Unsupervised Learning of Distributional Properties can Supplement Human Labeling and Increase Active Learning Efficiency in Anomaly Detection
Jaturong Kongmanee, Mark Chignell, Khilan Jerath +1
Exfiltration of data via email is a serious cybersecurity threat for many organizations. Detecting data exfiltration (anomaly) patterns typically requires labeling, most often done…