mlsanityData to 13 Oct 2026

Landscape of AI safety concerns -- A methodology to support safety assurance for AI-based autonomous systems

arXiv 2412.14020 ↗First posted 18 Dec 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) has emerged as a key technology, driving advancements across a range of applications. Its integration into modern autonomous systems requires assuring safety. However, the challenge of assuring safety in systems that incorporate AI components is substantial. The lack of concrete specifications, and also the complexity of both the operational environment and the system itself, leads to various aspects of uncertain behavior and complicates the derivation of convincing evidence for system safety. Nonetheless, scholars proposed to thoroughly analyze and mitigate AI-specific insufficiencies, so-called AI safety concerns, which yields essential evidence supporting a convincing assurance case. In this paper, we build upon this idea and propose the so-called Landscape of AI Safety Concerns, a novel methodology designed to support the creation of safety assurance cases for AI-based systems by systematically demonstrating the absence of AI safety concerns. The methodology's application is illustrated through a case study involving a driverless regional train, demonstrating its practicality and effectiveness.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

16 of 32 references.

References · 16

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,476
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,992
  4. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 670
  5. 2022Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetscited by 616
  6. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 411
  7. 2017Deep Learning is Robust to Massive Label Noisecited by 164
  8. 2021Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)cited by 42
  9. 2020Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodologycited by 41
  10. 2019Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challengescited by 39
  11. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  12. 2018Runtime Monitoring Neuron Activation Patternscited by 34
4 more
  1. 2020Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Taskscited by 31
  2. 2022Assurance Cases as Foundation Stone for Auditing AI-enabled and Autonomous Systems: Workshop Results and Political Recommendations for Action from the ExamAI Projectcited by 3
  3. 2023AI Hazard Management: A framework for the systematic management of root causes for AI riskscited by 3
  4. 2023Safety Performance of Neural Networks in the Presence of Covariate Shiftcited by 1

Built on by

Not cited yet.