# AI Maintenance: A Robustness Perspective

arXiv: https://arxiv.org/abs/2301.03052 · HTML: https://mlsanity.com/paper/2301.03052/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 8 Jan 2023.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning](https://mlsanity.com/paper/1804.00308/) (2018)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness](https://mlsanity.com/paper/2005.00060/) (2020)
- [Adversarial Machine Learning -- Industry Perspectives](https://mlsanity.com/paper/2002.05646/) (2020)
- [Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases](https://mlsanity.com/paper/2007.15802/) (2020)
- [Characterizing Audio Adversarial Examples Using Temporal Dependency](https://mlsanity.com/paper/1809.10875/) (2018)
- [FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity](https://mlsanity.com/paper/1808.07261/) (2018)
- [Holistic Adversarial Robustness of Deep Learning Models](https://mlsanity.com/paper/2202.07201/) (2022)
- [Self-Progressing Robust Training](https://mlsanity.com/paper/2012.11769/) (2020)

## Built on by (most cited first, 6 of 6)

- [Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation](https://mlsanity.com/paper/2305.02231/) (2023)
- [Test & Evaluation Best Practices for Machine Learning-Enabled Systems](https://mlsanity.com/paper/2310.06800/) (2023)
- [Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation](https://mlsanity.com/paper/2307.12520/) (2023)
- [Reliable agent engineering should integrate machine-compatible organizational principles](https://mlsanity.com/paper/2512.07665/) (2025)
- [NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing](https://mlsanity.com/paper/2407.20281/) (2024)
- [KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvement](https://mlsanity.com/paper/2608.02351/) (2026)

## Abstract (arXiv)

With the advancements in machine learning (ML) methods and compute resources, artificial intelligence (AI) empowered systems are becoming a prevailing technology. However, current AI technology such as deep learning is not flawless. The significantly increased model complexity and data scale incur intensified challenges when lacking trustworthiness and transparency, which could create new risks and negative impacts. In this paper, we carve out AI maintenance from the robustness perspective. We start by introducing some highlighted robustness challenges in the AI lifecycle and motivating AI maintenance by making analogies to car maintenance. We then propose an AI model inspection framework to detect and mitigate robustness risks. We also draw inspiration from vehicle autonomy to define the levels of AI robustness automation. Our proposal for AI maintenance facilitates robustness assessment, status tracking, risk scanning, model hardening, and regulation throughout the AI lifecycle, which is an essential milestone toward building sustainable and trustworthy AI ecosystems.