# Increasing the Confidence of Deep Neural Networks by Coverage Analysis

arXiv: https://arxiv.org/abs/2101.12100 · HTML: https://mlsanity.com/paper/2101.12100/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 58 references that are in the map.
- First posted on arXiv 28 Jan 2021.

## Builds on (most cited first, 30 of 43)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation](https://mlsanity.com/paper/1705.08475/) (2017)

## Built on by (most cited first, 9 of 9)

- [On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving](https://mlsanity.com/paper/2201.01850/) (2022)
- [Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis](https://mlsanity.com/paper/2203.07341/) (2022)
- [On the Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error](https://mlsanity.com/paper/2201.01235/) (2022)
- [Robust-by-Design Classification via Unitary-Gradient Neural Networks](https://mlsanity.com/paper/2209.04293/) (2022)
- [Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassifications](https://mlsanity.com/paper/2512.19472/) (2025)
- [Detection of Adversarial Physical Attacks in Time-Series Image Data](https://mlsanity.com/paper/2304.13919/) (2023)
- [DREAM: Debugging and Repairing AutoML Pipelines](https://mlsanity.com/paper/2401.00379/) (2023)
- [Ensembling Uncertainty Measures to Improve Safety of Black-Box Classifiers](https://mlsanity.com/paper/2308.12065/) (2023)
- [DeepCover: Advancing RNN Test Coverage and Online Error Prediction using State Machine Extraction](https://mlsanity.com/paper/2402.06966/) (2024)

## Abstract (arXiv)

The great performance of machine learning algorithms and deep neural networks in several perception and control tasks is pushing the industry to adopt such technologies in safety-critical applications, as autonomous robots and self-driving vehicles. At present, however, several issues need to be solved to make deep learning methods more trustworthy, predictable, safe, and secure against adversarial attacks. Although several methods have been proposed to improve the trustworthiness of deep neural networks, most of them are tailored for specific classes of adversarial examples, hence failing to detect other corner cases or unsafe inputs that heavily deviate from the training samples. This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model robustness against different unsafe inputs. In particular, four coverage analysis methods are proposed and tested in the architecture for evaluating multiple detection logics. Experimental results show that the proposed approach is effective in detecting both powerful adversarial examples and out-of-distribution inputs, introducing limited extra-execution time and memory requirements.