# Towards Rigorous Design of OoD Detectors

arXiv: https://arxiv.org/abs/2306.08447 · HTML: https://mlsanity.com/paper/2306.08447/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 4 references that are in the map.
- First posted on arXiv 14 Jun 2023.

## Builds on (most cited first, 2 of 2)

- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Logically Sound Arguments for the Effectiveness of ML Safety Measures](https://mlsanity.com/paper/2111.02649/) (2021)

## Built on by (most cited first, 1 of 1)

- [Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing](https://mlsanity.com/paper/2604.26411/) (2026)

## Abstract (arXiv)

Out-of-distribution (OoD) detection techniques are instrumental for safety-related neural networks. We are arguing, however, that current performance-oriented OoD detection techniques geared towards matching metrics such as expected calibration error, are not sufficient for establishing safety claims. What is missing is a rigorous design approach for developing, verifying, and validating OoD detectors. These design principles need to be aligned with the intended functionality and the operational domain. Here, we formulate some of the key technical challenges, together with a possible way forward, for developing a rigorous and safety-related design methodology for OoD detectors.