# Adversarial Examples on Object Recognition: A Comprehensive Survey

arXiv: https://arxiv.org/abs/2008.04094 · HTML: https://mlsanity.com/paper/2008.04094/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Adversarial Example Detection for DNN Models: A Review and Experimental Comparison](https://mlsanity.com/paper/2105.00203/) (2021)
- [A Review of Adversarial Attack and Defense for Classification Methods](https://mlsanity.com/paper/2111.09961/) (2021)
- [A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks](https://mlsanity.com/paper/2310.00633/) (2023)
- [Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2112.12310/) (2021)
- [Visual Adversarial Attacks and Defenses in the Physical World: A Survey](https://mlsanity.com/paper/2211.01671/) (2022)
- [Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective](https://mlsanity.com/paper/2101.03042/) (2021)
- [It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness](https://mlsanity.com/paper/2303.09767/) (2023)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [Energy-Latency Attacks: A New Adversarial Threat to Deep Learning](https://mlsanity.com/paper/2503.04963/) (2025)
- [A Survey of Neural Network Robustness Assessment in Image Recognition](https://mlsanity.com/paper/2404.08285/) (2024)
- [Monitoring Robustness and Individual Fairness](https://mlsanity.com/paper/2506.00496/) (2025)
- [A causal model of safety assurance for machine learning](https://mlsanity.com/paper/2201.05451/) (2022)
- [An Investigation of Visual Foundation Models Robustness](https://mlsanity.com/paper/2508.16225/) (2025)
- [Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration](https://mlsanity.com/paper/2102.04046/) (2021)
- [Guiding the retraining of convolutional neural networks against adversarial inputs](https://mlsanity.com/paper/2207.03689/) (2022)
- [Towards the Transferable Audio Adversarial Attack via Ensemble Methods](https://mlsanity.com/paper/2304.08811/) (2023)
- [Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR](https://mlsanity.com/paper/2401.17038/) (2024)
- [Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance](https://mlsanity.com/paper/2409.14401/) (2024)
- [A Domain-Theoretic Framework for Robustness Analysis of Neural Networks](https://mlsanity.com/paper/2203.00295/) (2022)
- [Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection](https://mlsanity.com/paper/2211.07483/) (2022)
- [Adversarial Detection by Approximation of Ensemble Boundary](https://mlsanity.com/paper/2211.10227/) (2022)
- [PEAS: A Strategy for Crafting Transferable Adversarial Examples](https://mlsanity.com/paper/2410.15409/) (2024)

## Abstract (arXiv)

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect behavior. Such perturbations, called adversarial examples, are intentionally designed to test the network's sensitivity to distribution drifts. Given their surprisingly small size, a wide body of literature conjectures on their existence and how this phenomenon can be mitigated. In this article we discuss the impact of adversarial examples on security, safety, and robustness of neural networks. We start by introducing the hypotheses behind their existence, the methods used to construct or protect against them, and the capacity to transfer adversarial examples between different machine learning models. Altogether, the goal is to provide a comprehensive and self-contained survey of this growing field of research.