# Empowering the trustworthiness of ML-based critical systems through engineering activities

arXiv: https://arxiv.org/abs/2209.15438 · HTML: https://mlsanity.com/paper/2209.15438/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 11 of 11)

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Engineering AI Systems: A Research Agenda](https://mlsanity.com/paper/2001.07522/) (2020)
- [White Paper Machine Learning in Certified Systems](https://mlsanity.com/paper/2103.10529/) (2021)
- [Towards Dependability Metrics for Neural Networks](https://mlsanity.com/paper/1806.02338/) (2018)
- [Security Risks in Deep Learning Implementations](https://mlsanity.com/paper/1711.11008/) (2017)
- [Data Engineering for Data Analytics: A Classification of the Issues, and Case Studies](https://mlsanity.com/paper/2004.12929/) (2020)
- [Data augmentation with Mobius transformations](https://mlsanity.com/paper/2002.02917/) (2020)
- [Practices for Engineering Trustworthy Machine Learning Applications](https://mlsanity.com/paper/2103.00964/) (2021)
- [Unit Tests for Stochastic Optimization](https://mlsanity.com/paper/1312.6055/) (2013)
- [An Orchestrated Empirical Study on Deep Learning Frameworks and Platforms](https://mlsanity.com/paper/1811.05187/) (2018)

## Abstract (arXiv)

This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions. We start from the fundamental principles of ML and describe the core elements conditioning its trust, particularly through its design: namely domain specification, data engineering, design of the ML algorithms, their implementation, evaluation and deployment. The latter components are organized in an unique framework for the design of trusted ML systems.