4 papers
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Haoyue Bai, Gregory Canal, Xuefeng Du +3
Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OO…
Towards Large Language Models for Lunar Mission Planning and In Situ Resource Utilization
Michael Pekala, Gregory Canal, Samuel Barham +5
A key factor for lunar mission planning is the ability to assess the local availability of raw materials. However, many potentially relevant measurements are scattered across a var…
A Decision-driven Methodology for Designing Uncertainty-aware AI Self-Assessment
Gregory Canal, Vladimir Leung, Philip Sage +2
Artificial intelligence (AI) has revolutionized decision-making processes and systems throughout society and, in particular, has emerged as a significant technology in high-impact…