# Universal Adversarial Perturbations: A Survey

arXiv: https://arxiv.org/abs/2005.08087 · HTML: https://mlsanity.com/paper/2005.08087/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2020.

## Built on by (most cited first, 28 of 28)

- [A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends](https://mlsanity.com/paper/2407.07403/) (2024)
- [A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions](https://mlsanity.com/paper/2202.11912/) (2022)
- [Test-Time Backdoor Attacks on Multimodal Large Language Models](https://mlsanity.com/paper/2402.08577/) (2024)
- [Continual Face Forgery Detection via Historical Distribution Preserving](https://mlsanity.com/paper/2308.06217/) (2023)
- [Stereoscopic Universal Perturbations across Different Architectures and Datasets](https://mlsanity.com/paper/2112.06116/) (2021)
- [Universal Spectral Adversarial Attacks for Deformable Shapes](https://mlsanity.com/paper/2104.03356/) (2021)
- [Improving Robustness by Enhancing Weak Subnets](https://mlsanity.com/paper/2201.12765/) (2022)
- [Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions](https://mlsanity.com/paper/2403.20254/) (2024)
- [A Study on FGSM Adversarial Training for Neural Retrieval](https://mlsanity.com/paper/2301.10576/) (2023)
- [ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems](https://mlsanity.com/paper/2201.02775/) (2022)
- [Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models](https://mlsanity.com/paper/2412.11423/) (2024)
- [Disrupting Adversarial Transferability in Deep Neural Networks](https://mlsanity.com/paper/2108.12492/) (2021)
- [Verifying Integrity of Deep Ensemble Models by Lossless Black-box Watermarking with Sensitive Samples](https://mlsanity.com/paper/2205.04145/) (2022)
- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Learning Visual Prompts for Guiding the Attention of Vision Transformers](https://mlsanity.com/paper/2406.03303/) (2024)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification](https://mlsanity.com/paper/2306.11261/) (2023)
- [How adversarial attacks can disrupt seemingly stable accurate classifiers](https://mlsanity.com/paper/2309.03665/) (2023)
- [ETA: Energy-based Test-time Adaptation for Depth Completion](https://mlsanity.com/paper/2508.05989/) (2025)
- [Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection](https://mlsanity.com/paper/2308.11480/) (2023)
- [You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries](https://mlsanity.com/paper/2102.00029/) (2021)
- [BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks](https://mlsanity.com/paper/2112.03477/) (2021)
- [Adversarial Robustness of Discriminative Self-Supervised Learning in Vision](https://mlsanity.com/paper/2503.06361/) (2025)
- [Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions](https://mlsanity.com/paper/2511.17380/) (2025)
- [Resilience of Autonomous Vehicle Object Category Detection to Universal Adversarial Perturbations](https://mlsanity.com/paper/2107.04749/) (2021)
- [Decorrelative Network Architecture for Robust Electrocardiogram Classification](https://mlsanity.com/paper/2207.09031/) (2022)
- [BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning](https://mlsanity.com/paper/2511.12046/) (2025)
- [When Interpretability Is Unequally Distributed: Fairness in Hybrid Interpretable Models](https://mlsanity.com/paper/2605.28626/) (2026)

## Abstract (arXiv)

Over the past decade, Deep Learning has emerged as a useful and efficient tool to solve a wide variety of complex learning problems ranging from image classification to human pose estimation, which is challenging to solve using statistical machine learning algorithms. However, despite their superior performance, deep neural networks are susceptible to adversarial perturbations, which can cause the network's prediction to change without making perceptible changes to the input image, thus creating severe security issues at the time of deployment of such systems. Recent works have shown the existence of Universal Adversarial Perturbations, which, when added to any image in a dataset, misclassifies it when passed through a target model. Such perturbations are more practical to deploy since there is minimal computation done during the actual attack. Several techniques have also been proposed to defend the neural networks against these perturbations. In this paper, we attempt to provide a detailed discussion on the various data-driven and data-independent methods for generating universal perturbations, along with measures to defend against such perturbations. We also cover the applications of such universal perturbations in various deep learning tasks.