# Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Tasks

arXiv: https://arxiv.org/abs/2001.08001 · HTML: https://mlsanity.com/paper/2001.08001/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2020.

## Built on by (most cited first, 30 of 31)

- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Labeling Neural Representations with Inverse Recognition](https://mlsanity.com/paper/2311.13594/) (2023)
- [Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection](https://mlsanity.com/paper/2110.09246/) (2021)
- [Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System](https://mlsanity.com/paper/2204.07874/) (2022)
- [Exposing Previously Undetectable Faults in Deep Neural Networks](https://mlsanity.com/paper/2106.00576/) (2021)
- [Deep Learning Safety Concerns in Automated Driving Perception](https://mlsanity.com/paper/2309.03774/) (2023)
- [A Review of Testing Object-Based Environment Perception for Safe Automated Driving](https://mlsanity.com/paper/2102.08460/) (2021)
- [Combating noisy labels in object detection datasets](https://mlsanity.com/paper/2211.13993/) (2022)
- [Requirement Engineering Challenges for AI-intense Systems Development](https://mlsanity.com/paper/2103.10270/) (2021)
- [Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study](https://mlsanity.com/paper/2405.20876/) (2024)
- [Quality Assurance Challenges for Machine Learning Software Applications During Software Development Life Cycle Phases](https://mlsanity.com/paper/2105.01195/) (2021)
- [Tailored Uncertainty Estimation for Deep Learning Systems](https://mlsanity.com/paper/2204.13963/) (2022)
- [Verifiable Obstacle Detection](https://mlsanity.com/paper/2208.14403/) (2022)
- [SURE-Val: Safe Urban Relevance Extension and Validation](https://mlsanity.com/paper/2308.02266/) (2023)
- [AI Hazard Management: A framework for the systematic management of root causes for AI risks](https://mlsanity.com/paper/2310.16727/) (2023)
- [Mitigating Shadows in Lidar Scan Matching using Spherical Voxels](https://mlsanity.com/paper/2208.01150/) (2022)
- [A Safety-Adapted Loss for Pedestrian Detection in Automated Driving](https://mlsanity.com/paper/2402.02986/) (2024)
- [Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey](https://mlsanity.com/paper/2511.05982/) (2025)
- [Single-Step Adversarial Training for Semantic Segmentation](https://mlsanity.com/paper/2106.15998/) (2021)
- [Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults](https://mlsanity.com/paper/2209.01710/) (2022)
- [Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement](https://mlsanity.com/paper/2401.10310/) (2024)
- [Methodology for an Analysis of Influencing Factors on 3D Object Detection Performance](https://mlsanity.com/paper/2411.08482/) (2024)
- [Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey](https://mlsanity.com/paper/2111.14324/) (2021)
- [Checklist to Define the Identification of TP, FP, and FN Object Detections in Automated Driving](https://mlsanity.com/paper/2308.07106/) (2023)
- [Learning-Based Error Detection System for Advanced Vehicle Instrument Cluster Rendering](https://mlsanity.com/paper/2409.02647/) (2024)
- [Landscape of AI safety concerns -- A methodology to support safety assurance for AI-based autonomous systems](https://mlsanity.com/paper/2412.14020/) (2024)
- [A Systematic Literature Review on Safety of the Intended Functionality for Automated Driving Systems](https://mlsanity.com/paper/2503.02498/) (2025)
- [A Machine Learning Perspective on Automated Driving Corner Cases](https://mlsanity.com/paper/2510.10653/) (2025)
- [Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception](https://mlsanity.com/paper/2604.20895/) (2026)

## Abstract (arXiv)

Deep learning methods are widely regarded as indispensable when it comes to designing perception pipelines for autonomous agents such as robots, drones or automated vehicles. The main reasons, however, for deep learning not being used for autonomous agents at large scale already are safety concerns. Deep learning approaches typically exhibit a black-box behavior which makes it hard for them to be evaluated with respect to safety-critical aspects. While there have been some work on safety in deep learning, most papers typically focus on high-level safety concerns. In this work, we seek to dive into the safety concerns of deep learning methods and present a concise enumeration on a deeply technical level. Additionally, we present extensive discussions on possible mitigation methods and give an outlook regarding what mitigation methods are still missing in order to facilitate an argumentation for the safety of a deep learning method.