# Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

arXiv: https://arxiv.org/abs/2104.14235 · HTML: https://mlsanity.com/paper/2104.14235/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 292 of its 454 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 30 of 292)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)

## Built on by (most cited first, 30 of 35)

- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [A Close Look into the Calibration of Pre-trained Language Models](https://mlsanity.com/paper/2211.00151/) (2022)
- [SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving](https://mlsanity.com/paper/2203.05056/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation](https://mlsanity.com/paper/2111.04875/) (2021)
- [Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving](https://mlsanity.com/paper/2107.07449/) (2021)
- [Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability](https://mlsanity.com/paper/2204.10598/) (2022)
- [Deep Learning Safety Concerns in Automated Driving Perception](https://mlsanity.com/paper/2309.03774/) (2023)
- [An Online Learning System for Wireless Charging Alignment using Surround-view Fisheye Cameras](https://mlsanity.com/paper/2105.12763/) (2021)
- [Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders](https://mlsanity.com/paper/2105.02965/) (2021)
- [Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving](https://mlsanity.com/paper/2210.08885/) (2022)
- [Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces](https://mlsanity.com/paper/2311.14435/) (2023)
- [Yes We Care! -- Certification for Machine Learning Methods through the Care Label Framework](https://mlsanity.com/paper/2105.10197/) (2021)
- [Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation](https://mlsanity.com/paper/2412.11608/) (2024)
- [A Survey on Uncertainty Toolkits for Deep Learning](https://mlsanity.com/paper/2205.01040/) (2022)
- [Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection](https://mlsanity.com/paper/2202.05123/) (2022)
- [Tailored Uncertainty Estimation for Deep Learning Systems](https://mlsanity.com/paper/2204.13963/) (2022)
- [SURE-Val: Safe Urban Relevance Extension and Validation](https://mlsanity.com/paper/2308.02266/) (2023)
- [Surround-View Cameras based Holistic Visual Perception for Automated Driving](https://mlsanity.com/paper/2206.05542/) (2022)
- [Broadening the perspective for sustainable AI: Comprehensive sustainability criteria and indicators for AI systems](https://mlsanity.com/paper/2306.13686/) (2023)
- [Statistical Challenges with Dataset Construction: Why You Will Never Have Enough Images](https://mlsanity.com/paper/2408.11160/) (2024)
- [Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems](https://mlsanity.com/paper/2510.21254/) (2025)
- [Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey](https://mlsanity.com/paper/2511.05982/) (2025)
- [The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning](https://mlsanity.com/paper/2106.00512/) (2021)
- [SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving](https://mlsanity.com/paper/2206.02876/) (2022)
- [Safe Perception -- A Hierarchical Monitor Approach](https://mlsanity.com/paper/2208.00824/) (2022)
- [Conditioning Latent-Space Clusters for Real-World Anomaly Classification](https://mlsanity.com/paper/2309.09676/) (2023)
- [OpenViGA: Video Generation for Automotive Driving Scenes by Streamlining and Fine-Tuning Open Source Models with Public Data](https://mlsanity.com/paper/2509.15479/) (2025)
- [Safe AI -- How is this Possible?](https://mlsanity.com/paper/2201.10436/) (2022)

## Abstract (arXiv)

The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability to problems with malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged. This work provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern ML methods. We moreover hope that our contribution fuels discussions on desiderata for ML systems and strategies on how to propel existing approaches accordingly.