34 citations · 52 across the 6 of their papers we have counts for
6 papers
Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression
T. Bauer, W. P. Kegelmeyer, E. Begoli +15
This article presents a structured framework of behavioral indicators that may signal progression toward potentially catastrophic threats from artificial intelligence systems. We a…
From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming
Anusha Sinha, Keltin Grimes, James Lucassen +4
A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI,…
Measuring AI Systems Beyond Accuracy
Violet Turri, Rachel Dzombak, Eric Heim +3
Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics. Testing is additionally often siloed from the oth…
On managing vulnerabilities in AI/ML systems
Jonathan M. Spring, April Galyardt, Allen D. Householder +1
This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems through a thought experiment: what if flaws in machine lear…
On the human-recognizability phenomenon of adversarially trained deep image classifiers
Jonathan Helland, Nathan VanHoudnos
In this work, we investigate the phenomenon that robust image classifiers have human-recognizable features -- often referred to as interpretability -- as revealed through the input…
Towards security defect prediction with AI
Carson D. Sestili, William S. Snavely, Nathan M. VanHoudnos
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 tools. To do so, we de…