Data to 7 Oct 2026

Generative Adversarial Perturbations

arXiv 1712.02328 ↗First posted 6 Dec 2017cs.CV cs.CR cs.LGcited by 153

Not on the map. Why?

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.

Key facts. Cited by 153 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 26; 2023: 30; 2024: 31; 2025: 21; 2026: 9.

153 papers.

Sort:

By area:

2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 260
2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
2021On Improving Adversarial Transferability of Vision Transformerscited by 70
2022Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbationcited by 67
2021On Generating Transferable Targeted Perturbationscited by 65
2021A Survey On Universal Adversarial Attackcited by 59
2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
2023Adversarial Counterfactual Visual Explanationscited by 47
2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Modelscited by 46
2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 39

38 more

2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 36
2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
2022Unlearnable Clusters: Towards Label-agnostic Unlearnable Examplescited by 35
2024Revisiting Adversarial Training at Scalecited by 33
2021Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networkscited by 31
2024Universal Adversarial Perturbations for Vision-Language Pre-trained Modelscited by 31
2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 29
2021Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformationscited by 28
2021Robust Feature-Level Adversaries are Interpretability Toolscited by 27
2021TAFIM: Targeted Adversarial Attacks against Facial Image Manipulationscited by 25
2021Removing Undesirable Feature Contributions Using Out-of-Distribution Datacited by 23
2022OPOM: Customized Invisible Cloak towards Face Privacy Protectioncited by 22
2023Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregationcited by 22
2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
2021Generative Dynamic Patch Attackcited by 19
2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
2024CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attackscited by 19
2021Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspectivecited by 18
2023Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibrationcited by 18
2021Attack to Fool and Explain Deep Networkscited by 17
2021Stereoscopic Universal Perturbations across Different Architectures and Datasetscited by 17
2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
2021Adversarial Imaging Pipelinescited by 15
2021Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attackcited by 15
2022More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networkscited by 15
2021Universal Spectral Adversarial Attacks for Deformable Shapescited by 14
2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
2022Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attackscited by 14
2023Mutual-modality Adversarial Attack with Semantic Perturbationcited by 14
2021Universal Adversarial Training with Class-Wise Perturbationscited by 13
2022GAMA: Generative Adversarial Multi-Object Scene Attackscited by 13
2021Generating Adversarial Examples with Graph Neural Networkscited by 12
2021Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systemscited by 12
2022Local Intensity Order Transformation for Robust Curvilinear Object Segmentationcited by 12
2022Imperceptible Adversarial Attack via Invertible Neural Networkscited by 12
2024Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensicscited by 12
2024As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?cited by 11

50 most cited of 153 All 153 (JSON)