mlsanityData to 7 Oct 2026

AI Maintenance: A Robustness Perspective

arXiv 2301.03052 ↗First posted 8 Jan 2023cs.LG cs.AI cs.CYcited by 6

Not on the map. Why?

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 8 Jan 2023.

Builds on

17 of 26 references.

References · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2018Datasheets for Datasetscited by 1,371
  6. 2018Model Cards for Model Reportingcited by 1,068
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  8. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  9. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  10. 2021Vision Transformers are Robust Learnerscited by 208
  11. 2020Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustnesscited by 130
  12. 2020Adversarial Machine Learning -- Industry Perspectivescited by 121
5 more
  1. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 93
  2. 2018Characterizing Audio Adversarial Examples Using Temporal Dependencycited by 34
  3. 2018FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformitycited by 31
  4. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  5. 2020Self-Progressing Robust Trainingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
  2. 2023Test & Evaluation Best Practices for Machine Learning-Enabled Systemscited by 3
  3. 2023Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translationcited by 2
  4. 2025Reliable agent engineering should integrate machine-compatible organizational principlescited by 2
  5. 2024NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicingcited by 1
  6. 2026KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvementcited by 0