mlsanityData to 14 Oct 2026

Adversarial Manipulation of Deep Representations

arXiv 1511.05122 ↗First posted 16 Nov 2015cs.CV cs.LG cs.NEcited by 56

Not on the map. Why?

Abstract (arXiv)

We show that the representation of an image in a deep neural network (DNN) can be manipulated to mimic those of other natural images, with only minor, imperceptible perturbations to the original image. Previous methods for generating adversarial images focused on image perturbations designed to produce erroneous class labels, while we concentrate on the internal layers of DNN representations. In this way our new class of adversarial images differs qualitatively from others. While the adversary is perceptually similar to one image, its internal representation appears remarkably similar to a different image, one from a different class, bearing little if any apparent similarity to the input; they appear generic and consistent with the space of natural images. This phenomenon raises questions about DNN representations, as well as the properties of natural images themselves.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 14; 2023: 16; 2024: 5; 2025: 2; 2026: 4.

56 papers.

Sort:

By area:

  1. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 205
  2. 2023Robust Classification via a Single Diffusion Modelcited by 79
  3. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  4. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  5. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  6. 2021Optical Adversarial Attackcited by 43
  7. 2023Don't trust your eyes: on the (un)reliability of feature visualizationscited by 32
  8. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 23
  9. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22
  10. 2021Feature Space Targeted Attacks by Statistic Alignmentcited by 21
  11. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  12. 2022Reverse Engineering of Imperceptible Adversarial Image Perturbationscited by 17
38 more
  1. 2024LLM Whisperer: An Inconspicuous Attack to Bias LLM Responsescited by 15
  2. 2022Adversarial Unlearning: Reducing Confidence Along Adversarial Directionscited by 14
  3. 2022Towards Lightweight Black-Box Attacks against Deep Neural Networkscited by 13
  4. 2021Staircase Sign Method for Boosting Adversarial Attackscited by 12
  5. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  6. 2023MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustnesscited by 12
  7. 2023Dynamic Adversarial Attacks on Autonomous Driving Systemscited by 11
  8. 2023SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detectioncited by 10
  9. 2025AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editingcited by 10
  10. 2022Adversarially Robust Learning with Tolerancecited by 9
  11. 2021What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Spacecited by 8
  12. 2021Adversarial Attack and Defense in Deep Rankingcited by 8
  13. 2021Performance Evaluation of Adversarial Attacks: Discrepancies and Solutionscited by 7
  14. 2023Splitting the Difference on Adversarial Trainingcited by 5
  15. 2023Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Modelscited by 5
  16. 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
  17. 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attackscited by 4
  18. 2021Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchycited by 4
  19. 2024Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patchescited by 4
  20. 2024Deep Learning Model Security: Threats and Defensescited by 4
  21. 2023Adversarial Medical Image with Hierarchical Feature Hidingcited by 3
  22. 2022Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) frameworkcited by 2
  23. 2022p-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representationscited by 2
  24. 2022Adversarial Detection: Attacking Object Detection in Real Timecited by 2
  25. 2023Exploring Geometry of Blind Spots in Vision Modelscited by 2
  26. 2021Delving into the pixels of adversarial samplescited by 1
  27. 2021On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examplescited by 1
  28. 2021Medical Aegis: Robust adversarial protectors for medical imagescited by 1
  29. 2022Superclass Adversarial Attackcited by 1
  30. 2022An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Modelscited by 1
  31. 2023Group-based Robustness: A General Framework for Customized Robustness in the Real Worldcited by 1
  32. 2023A reading survey on adversarial machine learning: Adversarial attacks and their understandingcited by 1
  33. 2023RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulationcited by 1
  34. 20242DSig-Detect: a semi-supervised framework for anomaly detection on image data using 2D-signaturescited by 1
  35. 2025Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environmentscited by 1
  36. 2026Robustness of Vision Language Models Against Split-Image Harmful Input Attackscited by 1
  37. 2021Target Training Does Adversarial Training Without Adversarial Samplescited by 0
  38. 2022Exact Feature Collisions in Neural Networkscited by 0

50 most cited of 56 All 56 (JSON)