Publications

Mar, 2026

Conference Paper

The Effects of Compounded Model Size Reductions on Adversarial Robustness

Recent advances in Edge AI and Tiny Machine Learning (TinyML) have enabled the deployment of machine learning models on resource-constrained environments. However, deploying these models on edge devices, such as micro-controllers, requires significant model footprint reduction through a variety of techniques such as quantization, pruning, and clustering. While these optimi…

Mar, 2026

Conference Paper

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are diff…

Mar, 2026

ORNL Report

ORNL AI Capabilities Summary

ORNL AI-powered capabilities in cybersecurity: CESER sponsor is cataloging AI-powered lab capabilities in cybersecurity and has asked us to complete this one-page template for each capability. These can be CESER-funded work, LDRD efforts, even projects or efforts funded by other agencies.) Note the request is for capability, not project.

Feb, 2026

Journal

ARCH: Large-scale knowledge graph via aggregated narrative codified health records analysis

Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes (NLP). The complexity of EHR presents challenges in feature representation, information extraction, and uncertainty quantification. To address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) re…

Feb, 2026

Book Chapter

Bridging the Gap from Research to Reality: Methods for Fortifying Mitigation Measures Against Adversarial AI

While research in the area of Adversarial AI and Mitigation (AAI&M) has quickly grown, research toward investigating the physical realizability of these methods has lagged behind. AAI&M Research often focuses on constrained or 2-Dimensional scenarios that don’t have direct translation to “in-the-wild” real-world problems. As example, an adversarial patch is often only gene…

Sep, 2025

Journal

Adversarial Binaries: AI-guided Instrumentation Methods for Malware Detection Evasion

Adversarial binaries are executable files that have been altered without loss of function by an AI agent in order to deceive malware detection systems. Progress in this emergent vein of research has been constrained by the complex and rigid structure of executable files. Although prior work has demonstrated that these binaries deceive a variety of malware classification mo…

Jun, 2025

Journal

Adversarial Binaries: AI-guided Instrumentation Methods for Malware Detection Evasion

Adversarial binaries are executable files that have been altered without loss of function by an AI agent in order to deceive malware detection systems. Progress in this emergent vein of research has been constrained by the complex and rigid structure of executable files. Although prior work has demonstrated that these binaries deceive a variety of malware classification mo…

Mar, 2025

Journal

Lantern: An Interactive Adversarial AI Workbench

Lantern, an innovative adversarial artificial intelligence (AI) workbench with unique features, is presented in this article. Lantern allows users to evaluate adversarial attacks quickly and interactively against artificial intelligence (AI) systems to protect them better. While there has been extensive work in assessing the robustness of AI models against attacks at a lar…

Jan, 2025

Journal

DOME: Directional medical embedding vectors from Electronic Health Records

Motivation: The increasing availability of Electronic Health Record (EHR) systems has created enormous potential for translational research. Recent developments in representation learning techniques have led to effective large-scale representations of EHR concepts along with knowledge graphs that empower downstream EHR studies. However, most existing methods require traini…

Dec, 2024

Journal

A Compound Data Poisoning Technique with Significant Adversarial Effects on Transformer-based Sentiment Classification Tasks

Transformer-based models have demonstrated much success in various natural language processing (NLP) tasks. However, they are often vulnerable to adversarial attacks, such as data poisoning, that can intentionally fool the model into generating incorrect results. In this paper, we present a novel, compound variant of a data poisoning attack on a transformer-based model tha…

Sep, 2024

Journal

An Emerging Role for Polystores in Precision Medicine

Medical data is organically heterogeneous, and it usually varies significantly in both size and composition. Yet, this data is also a key for the recent and promising field of precision medicine, which focuses on identifying and tailoring appropriate medical treatments for the needs of the individual patients, based on their specific conditions, their medical history, life…

Sep, 2024

Journal

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning