# Certifiable Artificial Intelligence Through Data Fusion

arXiv: https://arxiv.org/abs/2111.02001 · HTML: https://mlsanity.com/paper/2111.02001/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 55 references that are in the map.
- First posted on arXiv 3 Nov 2021.

## Builds on (most cited first, 9 of 9)

- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [Clustered Object Detection in Aerial Images](https://mlsanity.com/paper/1904.08008/) (2019)
- [Towards Verified Artificial Intelligence](https://mlsanity.com/paper/1606.08514/) (2016)
- [VIFB: A Visible and Infrared Image Fusion Benchmark](https://mlsanity.com/paper/2002.03322/) (2020)
- [Neural Network Verification in Control](https://mlsanity.com/paper/2110.01388/) (2021)
- [Blockchain Methods for Trusted Avionics Systems](https://mlsanity.com/paper/1910.10638/) (2019)
- [Artificial Intelligence Strategies for National Security and Safety Standards](https://mlsanity.com/paper/1911.05727/) (2019)
- [Multisource AI Scorecard Table for System Evaluation](https://mlsanity.com/paper/2102.03985/) (2021)

## Abstract (arXiv)

This paper reviews and proposes concerns in adopting, fielding, and maintaining artificial intelligence (AI) systems. While the AI community has made rapid progress, there are challenges in certifying AI systems. Using procedures from design and operational test and evaluation, there are opportunities towards determining performance bounds to manage expectations of intended use. A notional use case is presented with image data fusion to support AI object recognition certifiability considering precision versus distance.