Search Results - "VanHoudnos, Nathan"

On the Hedges Correction for a t-Test by VanHoudnos, Nathan M., Greenhouse, Joel B.

“…When cluster randomized experiments are analyzed as if units were independent, test statistics for treatment effects can be anticonservative. Hedges proposed a…”
Get full text

Prioritizing alerts from multiple static analysis tools, using classification models by Flynn, Lori, Snavely, William, Svoboda, David, VanHoudnos, Nathan, Qin, Richard, Burns, Jennifer, Zubrow, David, Stoddard, Robert, Marce-Santurio, Guillermo

“…Static analysis (SA) tools examine code for flaws without executing the code, and produce warnings ("alerts") about possible flaws. A human auditor then…”
Get full text

On the human-recognizability phenomenon of adversarially trained deep image classifiers by Helland, Jonathan, VanHoudnos, Nathan

“…In JSM Proceedings, Statistical Computing Section. Alexandria, VA: American Statistical Association. 1121-1131 (2020) In this work, we investigate the…”
Get full text

On managing vulnerabilities in AI/ML systems by Spring, Jonathan M, Galyardt, April, Householder, Allen D, VanHoudnos, Nathan

“…This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems through a thought experiment: what if…”
Get full text

Measuring AI Systems Beyond Accuracy by Turri, Violet, Dzombak, Rachel, Heim, Eric, VanHoudnos, Nathan, Palat, Jay, Sinha, Anusha

“…Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics. Testing is additionally…”
Get full text

Assessing LLMs for High Stakes Applications by Gallagher, Shannon K., Ratchford, Jasmine, Brooks, Tyler, Brown, Bryan, Heim, Eric, McMillan, Scott, Nichols, William R., Rallapalli, Swati, Smith, Carol, VanHoudnos, Nathan, Winski, Nick, Mellinger, Andrew O.

“…Large Language Models (LLMs) promise strategic benefit for numerous application domains. The current state-of-the-art in LLMs, however, lacks the trust,…”
Get full text

Towards security defect prediction with AI by Sestili, Carson D, Snavely, William S, VanHoudnos, Nathan M

“…In this study, we investigate the limits of the current state of the art AI system for detecting buffer overflows and compare it with current static analysis…”
Get full text