Data to 7 Oct 2026

A Self-supervised Approach for Adversarial Robustness

arXiv 2006.04924 ↗First posted 8 Jun 2020cs.CVcited by 180

Not on the map. Why?

Abstract (arXiv)

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock towards their real-world deployment. Transferability of adversarial examples demand generalizable defenses that can provide cross-task protection. Adversarial training that enhances robustness by modifying target model's parameters lacks such generalizability. On the other hand, different input processing based defenses fall short in the face of continuously evolving attacks. In this paper, we take the first step to combine the benefits of both approaches and propose a self-supervised adversarial training mechanism in the input space. By design, our defense is a generalizable approach and provides significant robustness against the unseen adversarial attacks (eg by reducing the success rate of translation-invariant ensemble attack from 82.6% to 31.9% in comparison to previous state-of-the-art). It can be deployed as a plug-and-play solution to protect a variety of vision systems, as we demonstrate for the case of classification, segmentation and detection. Code is available at: smallurlhttps://github.com/Muzammal-Naseer/NRP.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 25; 2023: 55; 2024: 28; 2025: 34; 2026: 10.

180 papers.

Sort:

By area:

2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155
2022Frequency Domain Model Augmentation for Adversarial Attackcited by 128
2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
2023AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learningcited by 101
2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
2022Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbationcited by 67
2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Modelscited by 66
2021On Generating Transferable Targeted Perturbationscited by 65

38 more

2023Boosting Adversarial Transferability by Block Shuffle and Rotationcited by 64
2023Structure Invariant Transformation for better Adversarial Transferabilitycited by 61
2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
2023Boosting Adversarial Transferability by Achieving Flat Local Maximacited by 48
2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Modelscited by 46
2021Online Adversarial Purification based on Self-Supervisioncited by 45
2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
2021Biometrics: Trust, but Verifycited by 39
2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Modelscited by 39
2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
2023Diversifying the High-level Features for better Adversarial Transferabilitycited by 34
2023Downstream-agnostic Adversarial Examplescited by 32
2024DarkSAM: Fooling Segment Anything Model to Segment Nothingcited by 32
2021Unified Detection of Digital and Physical Face Attackscited by 31
2022Boosting the Transferability of Adversarial Attacks with Global Momentum Initializationcited by 29
2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
2023Rethinking the Backward Propagation for Adversarial Transferabilitycited by 27
2024Learning to Transform Dynamically for Better Adversarial Transferabilitycited by 23
2021Adaptive Image Transformations for Transfer-based Adversarial Attackcited by 22
2023Improving Adversarial Transferability by Stable Diffusioncited by 22
2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
2024Securely Fine-tuning Pre-trained Encoders Against Adversarial Examplescited by 21
2023Defending against Adversarial Audio via Diffusion Modelcited by 20
2023Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibrationcited by 18
2022Is Self-Supervised Learning More Robust Than Supervised Learning?cited by 17
2021Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learningcited by 16
2022Pre-trained Adversarial Perturbationscited by 16
2022Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learningcited by 15
2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
2023Defenses in Adversarial Machine Learning: A Surveycited by 14
2021Learning to Learn Transferable Attackcited by 13
2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
2022GAMA: Generative Adversarial Multi-Object Scene Attackscited by 13
2023Improving the Transferability of Adversarial Examples with Arbitrary Style Transfercited by 13
2021Learning Diverse-Structured Networks for Adversarial Robustnesscited by 12
2021Adversarial example generation with AdaBelief Optimizer and Crop Invariancecited by 12

50 most cited of 180 All 180 (JSON)