# Generative Adversarial Perturbations

arXiv: https://arxiv.org/abs/1712.02328 · HTML: https://mlsanity.com/paper/1712.02328/

## Key facts

- Cited by 153 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2017.

## Built on by (most cited first, 30 of 153)

- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [On Improving Adversarial Transferability of Vision Transformers](https://mlsanity.com/paper/2106.04169/) (2021)
- [Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation](https://mlsanity.com/paper/2210.05968/) (2022)
- [On Generating Transferable Targeted Perturbations](https://mlsanity.com/paper/2103.14641/) (2021)
- [A Survey On Universal Adversarial Attack](https://mlsanity.com/paper/2103.01498/) (2021)
- [FedFed: Feature Distillation against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2310.05077/) (2023)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models](https://mlsanity.com/paper/2307.12499/) (2023)
- [A Survey on Transferability of Adversarial Examples across Deep Neural Networks](https://mlsanity.com/paper/2310.17626/) (2023)
- [Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains](https://mlsanity.com/paper/2201.11528/) (2022)
- [One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models](https://mlsanity.com/paper/2406.05491/) (2024)
- [Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective](https://mlsanity.com/paper/2210.04213/) (2022)
- [Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples](https://mlsanity.com/paper/2301.01217/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Revisiting Adversarial Training at Scale](https://mlsanity.com/paper/2401.04727/) (2024)
- [Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks](https://mlsanity.com/paper/2107.01809/) (2021)
- [Universal Adversarial Perturbations for Vision-Language Pre-trained Models](https://mlsanity.com/paper/2405.05524/) (2024)
- [Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses](https://mlsanity.com/paper/2104.01789/) (2021)
- [Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations](https://mlsanity.com/paper/2110.01823/) (2021)
- [Robust Feature-Level Adversaries are Interpretability Tools](https://mlsanity.com/paper/2110.03605/) (2021)
- [TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations](https://mlsanity.com/paper/2112.09151/) (2021)
- [Removing Undesirable Feature Contributions Using Out-of-Distribution Data](https://mlsanity.com/paper/2101.06639/) (2021)
- [Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey](https://mlsanity.com/paper/2410.23687/) (2024)
- [OPOM: Customized Invisible Cloak towards Face Privacy Protection](https://mlsanity.com/paper/2205.11981/) (2022)
- [Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation](https://mlsanity.com/paper/2308.06015/) (2023)
- [Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective](https://mlsanity.com/paper/2302.09457/) (2023)
- [Generative Dynamic Patch Attack](https://mlsanity.com/paper/2111.04266/) (2021)
- [A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks](https://mlsanity.com/paper/2310.00633/) (2023)
- [CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks](https://mlsanity.com/paper/2407.10179/) (2024)

## Abstract (arXiv)

In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce image-agnostic and image-dependent perturbations for both targeted and non-targeted attacks. We also demonstrate that similar architectures can achieve impressive results in fooling classification and semantic segmentation models, obviating the need for hand-crafting attack methods for each task. Using extensive experiments on challenging high-resolution datasets such as ImageNet and Cityscapes, we show that our perturbations achieve high fooling rates with small perturbation norms. Moreover, our attacks are considerably faster than current iterative methods at inference time.