# Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2409.03458 · HTML: https://mlsanity.com/paper/2409.03458/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 58 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 27 of 27)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [Recent Trends in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/1708.02709/) (2017)
- [Adversarial Examples that Fool both Computer Vision and Time-Limited Humans](https://mlsanity.com/paper/1802.08195/) (2018)
- [AdvFaces: Adversarial Face Synthesis](https://mlsanity.com/paper/1908.05008/) (2019)
- [Defense against Universal Adversarial Perturbations](https://mlsanity.com/paper/1711.05929/) (2017)
- [Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study](https://mlsanity.com/paper/2003.11145/) (2020)
- [Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations](https://mlsanity.com/paper/2202.04235/) (2022)
- [Adversarial Relighting Against Face Recognition](https://mlsanity.com/paper/2108.07920/) (2021)
- [FaceGuard: A Self-Supervised Defense Against Adversarial Face Images](https://mlsanity.com/paper/2011.14218/) (2020)
- [Color Channel Perturbation Attacks for Fooling Convolutional Neural Networks and A Defense Against Such Attacks](https://mlsanity.com/paper/2012.14456/) (2020)
- [On Brightness Agnostic Adversarial Examples Against Face Recognition Systems](https://mlsanity.com/paper/2109.14205/) (2021)
- [Powerful Physical Adversarial Examples Against Practical Face Recognition Systems](https://mlsanity.com/paper/2203.15498/) (2022)
- [Perturbation Inactivation Based Adversarial Defense for Face Recognition](https://mlsanity.com/paper/2207.06035/) (2022)
- [AdaNorm: Adaptive Gradient Norm Correction based Optimizer for CNNs](https://mlsanity.com/paper/2210.06364/) (2022)
- [Random Transformation of Image Brightness for Adversarial Attack](https://mlsanity.com/paper/2101.04321/) (2021)
- [Enhancing object detection robustness: A synthetic and natural perturbation approach](https://mlsanity.com/paper/2304.10622/) (2023)
- [AdaInject: Injection Based Adaptive Gradient Descent Optimizers for Convolutional Neural Networks](https://mlsanity.com/paper/2109.12504/) (2021)

## Built on by (most cited first, 2 of 2)

- [Toward Carbon-Neutral Human AI: Rethinking Data, Computation, and Learning Paradigms for Sustainable Intelligence](https://mlsanity.com/paper/2510.23524/) (2025)
- [Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning](https://mlsanity.com/paper/2605.22169/) (2026)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have made remarkable strides; however, they remain susceptible to vulnerabilities, particularly in the face of minor image perturbations that humans can easily recognize. This weakness, often termed as 'attacks', underscores the limited robustness of CNNs and the need for research into fortifying their resistance against such manipulations. This study introduces a novel Non-Uniform Illumination (NUI) attack technique, where images are subtly altered using varying NUI masks. Extensive experiments are conducted on widely-accepted datasets including CIFAR10, TinyImageNet, and CalTech256, focusing on image classification with 12 different NUI attack models. The resilience of VGG, ResNet, MobilenetV3-small and InceptionV3 models against NUI attacks are evaluated. Our results show a substantial decline in the CNN models' classification accuracy when subjected to NUI attacks, indicating their vulnerability under non-uniform illumination. To mitigate this, a defense strategy is proposed, including NUI-attacked images, generated through the new NUI transformation, into the training set. The results demonstrate a significant enhancement in CNN model performance when confronted with perturbed images affected by NUI attacks. This strategy seeks to bolster CNN models' resilience against NUI attacks.