mlsanityData to 7 Oct 2026

Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

arXiv 1801.04693 ↗First posted 15 Jan 2018cs.LG cs.CR stat.MLcited by 38

Not on the map. Why?

Abstract (arXiv)

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbations to the input. Previous adversarial example crafting methods, however, use simple metrics to evaluate the distances between the original examples and the adversarial ones, which could be easily detected by human eyes. In addition, these attacks are often not robust due to the inevitable noises and deviation in the physical world. In this work, we present a new adversarial example attack crafting method, which takes the human perceptual system into consideration and maximizes the noise tolerance of the crafted adversarial example. Experimental results demonstrate the efficacy of the proposed technique.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 6; 2023: 8; 2024: 8; 2025: 6.

38 papers.

Sort:

By area:

  1. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  2. 2021A Comprehensive Evaluation Framework for Deep Model Robustnesscited by 41
  3. 2021Delving into Data: Effectively Substitute Training for Black-box Attackcited by 27
  4. 2021Unsupervised Robust Domain Adaptation without Source Datacited by 19
  5. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  6. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 14
  7. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-artcited by 14
  8. 2022Why adversarial training can hurt robust accuracycited by 12
  9. 2022Imperceptible Adversarial Attack via Invertible Neural Networkscited by 12
  10. 2022fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systemscited by 8
  11. 2023FedRight: An Effective Model Copyright Protection for Federated Learningcited by 8
  12. 2024Imperceptible Protection against Style Imitation from Diffusion Modelscited by 8
26 more
  1. 2021Integer-arithmetic-only Certified Robustness for Quantized Neural Networkscited by 7
  2. 2025AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attackscited by 7
  3. 2024Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Modelscited by 6
  4. 2021Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extractioncited by 5
  5. 2023Exploring Adversarial Attacks on Neural Networks: An Explainable Approachcited by 4
  6. 2023Generating Robust Adversarial Examples against Online Social Networks (OSNs)cited by 4
  7. 2024MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protectioncited by 4
  8. 2024Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysiscited by 4
  9. 2021Fashion-Guided Adversarial Attack on Person Segmentationcited by 3
  10. 2021Amicable Aid: Perturbing Images to Improve Classification Performancecited by 3
  11. 2024Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairnesscited by 3
  12. 2022Robust Universal Adversarial Perturbationscited by 2
  13. 2023NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attackscited by 2
  14. 2025Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensemblescited by 2
  15. 2023ExploreADV: Towards exploratory attack for Neural Networkscited by 1
  16. 2024Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learningcited by 1
  17. 2025Defending Against Frequency-Based Attacks with Diffusion Modelscited by 1
  18. 2025IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimizationcited by 1
  19. 2021Towards Imperceptible Query-limited Adversarial Attacks with Perceptual Feature Fidelity Losscited by 0
  20. 2021Generating Structured Adversarial Attacks Using Frank-Wolfe Methodcited by 0
  21. 2022Multi-step domain adaptation by adversarial attack to H Delta H-divergencecited by 0
  22. 2023The Power of Typed Affine Decision Structures: A Case Studycited by 0
  23. 2024Is ReLU Adversarially Robust?cited by 0
  24. 2024PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attackscited by 0
  25. 2025FRAUD-RLA: A new reinforcement learning adversarial attack against credit card fraud detectioncited by 0
  26. 2025Towards Assessing Deep Learning Test Input Generatorscited by 0