mlsanityData to 14 Oct 2026

Exploring the Space of Adversarial Images

arXiv 1510.05328 ↗First posted 19 Oct 2015cs.NEcited by 28

Not on the map. Why?

Abstract (arXiv)

Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images appear in large regions in the pixel space, but that, for the same task, a shallow classifier seems more robust to adversarial images than a deep convolutional network.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Oct 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 3; 2023: 7; 2024: 4; 2025: 2; 2026: 1.

28 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identificationcited by 42
  3. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 23
  4. 2021Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspectivecited by 18
  5. 2023SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detectioncited by 10
  6. 2021Domain Invariant Adversarial Learningcited by 7
  7. 2023Identifying Adversarially Attackable and Robust Samplescited by 5
  8. 2023Splitting the Difference on Adversarial Trainingcited by 5
  9. 2025Atmospheric Predictability Beyond 30 Days with Machine Learningcited by 5
  10. 2023On the Relationship Between Interpretability and Explainability in Machine Learningcited by 3
  11. 2024Targeted Deep Learning System Boundary Testingcited by 3
  12. 2021Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustnesscited by 2
16 more
  1. 2022Evaluation of Neural Networks Defenses and Attacks using NDCG and Reciprocal Rank Metricscited by 2
  2. 2024Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysiscited by 2
  3. 2021Understanding Robustness in Teacher-Student Setting: A New Perspectivecited by 1
  4. 2021Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networkscited by 1
  5. 2022Guidance Through Surrogate: Towards a Generic Diagnostic Attackcited by 1
  6. 2023Learning video embedding space with Natural Language Supervisioncited by 1
  7. 2021Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbationscited by 0
  8. 2021Visualizing Representations of Adversarially Perturbed Inputscited by 0
  9. 2021Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspectivecited by 0
  10. 2021Multi-concept adversarial attackscited by 0
  11. 2022Efficiently Finding Adversarial Examples with DNN Preprocessingcited by 0
  12. 2023On-Manifold Projected Gradient Descentcited by 0
  13. 2023F2AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patternscited by 0
  14. 2024Dynamic Gradient Influencing for Viral Marketing Using Graph Neural Networkscited by 0
  15. 2025The Built-In Robustness of Decentralized Federated Averaging to Bad Datacited by 0
  16. 2026Towards Robust Universal Perturbation Attacks: A Float-Coded, Penalty-Driven Evolutionary Approachcited by 0