mlsanityData to 7 Oct 2026

IPatch: A Remote Adversarial Patch

arXiv 2105.00113 ↗First posted 30 Apr 2021cs.CV cs.AI cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

Applications such as autonomous vehicles and medical screening use deep learning models to localize and identify hundreds of objects in a single frame. In the past, it has been shown how an attacker can fool these models by placing an adversarial patch within a scene. However, these patches must be placed in the target location and do not explicitly alter the semantics elsewhere in the image. In this paper, we introduce a new type of adversarial patch which alters a model's perception of an image's semantics. These patches can be placed anywhere within an image to change the classification or semantics of locations far from the patch. We call this new class of adversarial examples `remote adversarial patches' (RAP). We implement our own RAP called IPatch and perform an in-depth analysis on image segmentation RAP attacks using five state-of-the-art architectures with eight different encoders on the CamVid street view dataset. Moreover, we demonstrate that the attack can be extended to object recognition models with preliminary results on the popular YOLOv3 model. We found that the patch can change the classification of a remote target region with a success rate of up to 93% on average.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 44 of its 73 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

44 of 73 references.

References · 44

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2018YOLOv3: An Incremental Improvementcited by 2,652
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  8. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  9. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  11. 2017Dynamic Routing Between Capsulescited by 689
  12. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
32 more
  1. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  2. 2017Adversarial Patchcited by 514
  3. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  4. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  5. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  6. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 212
  7. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  8. 2018Physical Adversarial Examples for Object Detectorscited by 163
  9. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  10. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  11. 2018Pyramid Attention Network for Semantic Segmentationcited by 148
  12. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  13. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  14. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  15. 2017Dual Path Networkscited by 119
  16. 2018Transferable Adversarial Attacks for Image and Video Object Detectioncited by 109
  17. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  18. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  19. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  20. 2016MultiNet: Real-time Joint Semantic Reasoning for Autonomous Drivingcited by 90
  21. 2018Learning to predict crisp boundariescited by 81
  22. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  23. 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
  24. 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
  25. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  26. 2015Foveation-based Mechanisms Alleviate Adversarial Examplescited by 32
  27. 2019CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learningcited by 31
  28. 2019Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentationcited by 26
  29. 2020Object Hider: Adversarial Patch Attack Against Object Detectorscited by 23
  30. 2020Dynamic Adversarial Patch for Evading Object Detection Modelscited by 20
  31. 2020Adversarial Patch Camouflage against Aerial Detectioncited by 16
  32. 2017Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competitioncited by 10

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 2.

7 papers.

  1. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  2. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  3. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  4. 2023Distributional Modeling for Location-Aware Adversarial Patchescited by 3
  5. 2024Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinementcited by 2
  6. 2023DTA: Distribution Transform-based Attack for Query-Limited Scenariocited by 0
  7. 2024Enhancing Remote Adversarial Patch Attacks on Face Detectors with Tiling and Scalingcited by 0