CoChat
Sign Up
Cited by 13Adversarial Robustness in Machine LearningDigital Media Forensic DetectionAdvanced Neural Network Applications

The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.

From Pixel to Peril: Investigating Adversarial Attacks on Aerial Imagery Through Comprehensive Review and Prospective Trajectories

Open access
Kazmi, Syed M. Kazam Abbas, Aafaq, Nayyer, Khan, Mansoor Ahmed, Khalil, Mohsin, Saleem, Ammar·2023·IEEE Access
DOI 10.1109/access.2023.3299878
Open this paper in CoChat — free accountOpen PDF

Abstract

Deep models’ feature learning capabilities have gained traction in recent years, driving significant progress in various Artificial Intelligence (AI) domains. The use of Deep Neural Networks (DNNs) has expanded the scope of Computer Vision (CV) and revealed their vulnerability to deliberate adversarial attacks. These attacks involve the careful introduction of perturbations crafted through complex optimization problems. Exploiting vulnerabilities in advanced deep neural network algorithms present security concerns, particularly in practical applications with high stakes like unmanned aerial vehicles (UAVs) and satellite imagery in computer vision. Adversarial attacks, both in digital and physical dimensions, pose a serious threat in the field. This research provides a comprehensive examination of state-of-the-art adversarial attacks specific to aerial imagery using autonomous platforms such as UAVs and satellites. This review covers fundamental concepts, techniques, and the latest advancements, identifying research gaps and suggesting future directions. It aims to deepen researchers’ understanding of the challenges and threats related to adversarial attacks on aerial imagery, serving as a valuable resource to guide future research and enhance the security of computer vision systems in aerial environments.

Overview

Integrity signals

Registry

Crossref · 10.1109/access.2023.3299878

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 12 references

Research works printed but not linked: 177

  1. 10.1109/PerCom45495.2020.9127389 · DOI
  2. 10.1109/TVT.2021.3061065 · DOI
  3. 10.1109/JIOT.2020.3016145 · DOI
  4. 10.1109/IV51971.2022.9827222 · DOI
  5. 10.3390/electronics9081284 · DOI
  6. 10.1007/s11042-019-7262-8 · DOI
  7. 10.1109/AIPR50011.2020.9425267 · DOI
  8. 10.1109/AIPR57179.2022.10092201 · DOI
  9. 10.1109/ACCESS.2020.3024149 · DOI
  10. wise, 2022, Developing imperceptible adversarial patches to camouflage military assets from computer vision enabled technologies, arXiv 2202 08892
  11. 10.1007/978-1-4842-6168-2_6 · DOI
  12. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  13. 10.24963/ijcai.2021/173 · DOI
  14. 10.3390/electronics12091987 · DOI
  15. 10.1007/978-3-030-87664-7_7 · DOI
  16. 10.1016/j.neucom.2023.03.050 · DOI
  17. 10.1109/TGRS.2022.3183022 · DOI
  18. 10.1109/TGRS.2023.3264839 · DOI
  19. 10.1109/TGRS.2022.3225306 · DOI
  20. 10.1109/TGRS.2023.3273287 · DOI
  21. 10.1109/CVPRW.2019.00012 · DOI
  22. 10.1007/978-3-030-58558-7_39 · DOI
  23. 10.1109/CVPR.2019.00790 · DOI
  24. cherepanova, 2021, LowKey: Leveraging adversarial attacks to protect social media users from facial recognition, arXiv 2101 07922
  25. wei, 2022, Physical adversarial attacks and defenses in computer vision: A survey, arXiv 2211 01671
  26. 10.1109/CVPR.2016.282 · DOI · Paper page
  27. lei, 2022, Using frequency attention to make adversarial patch powerful against person detector, arXiv 2205 04638
  28. simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv 1409 1556
  29. 10.1609/aaai.v35i4.16477 · DOI
  30. 10.1016/j.patrec.2021.04.004 · DOI
  31. 10.1061/(ASCE)IS.1943-555X.0000477 · DOI
  32. 10.1007/s42452-021-04897-7 · DOI
  33. 10.1016/B978-0-12-818464-6.00006-8 · DOI
  34. 10.1007/978-3-031-09753-9_7 · DOI
  35. 10.1016/j.compag.2021.106014 · DOI
  36. 10.3390/rs13030516 · DOI
  37. steven, 2013, Applications of Remote Sensing in Agriculture
  38. abid, 2022, A review on the application of remote sensing and geographic information system in flood crisis management, Proc Conf Broad Exposure Sci Technol, 1
  39. 10.1609/aaai.v36i2.20141 · DOI
  40. liu, 2016, SSD: Single shot multibox detector, Proc 14th Eur Conf, 21
  41. 10.1109/CVPR46437.2021.00846 · DOI
  42. 10.1109/SP.2017.49 · DOI · Paper page
  43. lee, 2019, On physical adversarial patches for object detection, arXiv 1906 11897
  44. 10.1109/CVPR.2017.690 · DOI · Paper page
  45. 10.1109/ICCV.2015.169 · DOI · Paper page
  46. bochkovskiy, 2020, YOLOv4: Optimal speed and accuracy of object detection, arXiv 2004 10934
  47. redmon, 2018, YOLOv3: An incremental improvement, arXiv 1804 02767
  48. madry, 2017, Towards deep learning models resistant to adversarial attacks, arXiv 1706 06083
  49. 10.1016/j.cosrev.2019.100199 · DOI
  50. 10.1109/SP.2016.41 · DOI
  51. 10.1109/MMSP55362.2022.9948869 · DOI
  52. gu, 2014, Towards deep neural network architectures robust to adversarial examples, arXiv 1412 5068 [cs]
  53. 10.1145/3274895.3274904 · DOI
  54. kannan, 2018, Adversarial logit pairing, arXiv 1803 06373
  55. 10.1109/JPROC.2022.3223186 · DOI
  56. wang, 2016, A theoretical framework for robustness of (deep) classifiers against adversarial examples, arXiv 1612 00334
  57. 10.1109/CVPR.2018.00957 · DOI
  58. biggio, 2012, Poisoning attacks against support vector machines, arXiv 1206 6389
  59. 10.3390/s20041226 · DOI
  60. 10.3390/rs13204078 · DOI
  61. 10.1109/JPROC.2017.2675998 · DOI · Paper page
  62. 10.1145/1869790.1869829 · DOI
  63. 10.1109/CVPR.2018.00418 · DOI · Paper page
  64. chen, 2019, Adversarial example in remote sensing image recognition, arXiv 1910 13222
  65. 10.1109/CVPR.2018.00646 · DOI · Paper page
  66. 10.1109/TIFS.2022.3226905 · DOI
  67. szegedy, 2013, Intriguing properties of neural networks, arXiv 1312 6199
  68. goodfellow, 2014, Explaining and harnessing adversarial examples, arXiv 1412 6572
  69. 10.1109/LGRS.2019.2930308 · DOI
  70. 10.1109/TGRS.2022.3156392 · DOI
  71. 10.1109/AIPR.2017.8457969 · DOI
  72. 10.1145/3097983.3098070 · DOI
  73. 10.1109/TGRS.2016.2645610 · DOI
  74. papernot, 2016, Transferability in machine learning: From phenomena to black-box attacks using adversarial samples, arXiv 1605 07277
  75. 10.1201/9781351251389-8 · DOI · Paper page
  76. carlini, 2017, MagNet and ‘efficient defenses against adversarial attacks’ are not robust to adversarial examples, arXiv 1711 08478
  77. 10.3390/rs14215298 · DOI
  78. 10.1109/ICCVW.2019.00030 · DOI
  79. lin, 2014, Microsoft COCO: Common objects in context, Proc 13th Eur Conf, 740
  80. 10.3390/rs9040368 · DOI
  81. 10.1109/WACV51458.2022.00385 · DOI
  82. 10.1109/TGRS.2017.2685945 · DOI · Paper page
  83. 10.1109/CVPRW.2015.7301377 · DOI · Paper page
  84. 10.1109/TASL.2011.2109382 · DOI
  85. 10.1109/TAI.2021.3134190 · DOI
  86. 10.1109/CVPR42600.2020.01291 · DOI
  87. qin, 2020, BiPointNet: Binary neural network for point clouds, arXiv 2010 05501
  88. guo, 2020, Backpropagating linearly improves transferability of adversarial examples, Proc Adv Neural Inf Process Syst, 33, 85
  89. 10.1109/ICPR48806.2021.9412236 · DOI · Paper page
  90. 10.1109/CVPR.2019.00445 · DOI
  91. li, 2019, Adversarial camera stickers: A physical camera-based attack on deep learning systems, Proc Int Conf Mach Learn, 3896
  92. 10.1109/CVPR.2019.01161 · DOI
  93. 10.1145/3355390 · DOI
  94. 10.1109/CVPR46437.2021.01498 · DOI
  95. 10.1109/CVPR46437.2021.01579 · DOI
  96. 10.1007/s10846-016-0464-7 · DOI
  97. wu, 2020, Physical adversarial attack on vehicle detector in the Carla simulator, arXiv 2007 16118
  98. 10.1109/CVPR.2017.17 · DOI · Paper page
  99. 10.1109/TMM.2022.3146005 · DOI
  100. 10.1109/CVPR.2019.01277 · DOI
  101. 10.1155/2022/9580991 · DOI
  102. 10.1016/j.jksues.2020.06.001 · DOI
  103. 10.1109/WACV51458.2022.00288 · DOI
  104. 10.1109/CVPR42600.2020.00044 · DOI
  105. 10.1007/978-3-030-58601-0_24 · DOI
  106. 10.1109/CVPR42600.2020.00130 · DOI
  107. zhang, 2018, CAMOU: Learning physical vehicle camouflages to adversarially attack detectors in the wild, Proc Int Conf Learn Represent, 1
  108. 10.1109/CVPR42600.2020.00847 · DOI
  109. 10.1145/3548606.3560566 · DOI
  110. 10.1109/CVPR42600.2020.00111 · DOI
  111. sriramanan, 2020, Guided adversarial attack for evaluating and enhancing adversarial defenses, Proc Adv Neural Inf Process Syst, 33, 20297
  112. 10.1109/SIBIRCON48586.2019.8958134 · DOI
  113. 10.1109/ICCV.2019.00843 · DOI
  114. 10.1609/aaai.v33i01.33011028 · DOI
  115. 10.1109/TPAMI.2022.3169802 · DOI
  116. 10.1145/2810103.2813677 · DOI · Paper page
  117. wei, 2023, Adversarial sticker: A stealthy attack method in the physical world, IEEE Trans Pattern Anal Mach Intell, 45, 2711
  118. 10.1109/CVPR.2018.00175 · DOI · Paper page
  119. 10.1109/ACCESS.2023.3234313 · DOI
  120. brown, 2017, Adversarial patch, arXiv 1712 09665
  121. ru, 2020, BayesOpt adversarial attack, Proc Int Conf Learn Represent, 1
  122. dickson, 2023, New Deep Learning Model Brings Image Segmentation to Edge Devices
  123. wei, 2021, Generating transferable adversarial patch by simultaneously optimizing its position and perturbations, Proc ICLR, 1
  124. 10.1145/3243734.3264418 · DOI
  125. 10.3390/urbansci5030068 · DOI
  126. 10.1109/EuroSP.2016.36 · DOI · Paper page
  127. 10.1109/ROBOT.2010.5509934 · DOI
  128. xu, 2017, Feature squeezing: Detecting adversarial examples in deep neural networks, arXiv 1704 01155
  129. 10.1109/IJCNN.2016.7727230 · DOI
  130. 10.1117/12.2575907 · DOI
  131. 10.1109/TPAMI.2018.2858821 · DOI
  132. 10.1109/TEVC.2019.2890858 · DOI · Paper page
  133. 10.1109/ICAI58407.2023.10136660 · DOI
  134. bhambri, 2019, A survey of black-box adversarial attacks on computer vision models, arXiv 1912 01667
  135. 10.1007/978-3-030-58548-8_1 · DOI
  136. jin, 2020, Adversarial attacks and defenses on graphs: A review, a tool and empirical studies, arXiv 2003 00653
  137. 10.1109/ICCV48922.2021.00775 · DOI
  138. athalye, 2018, Synthesizing robust adversarial examples, Proc Int Conf Mach Learn, 284
  139. 10.1109/CVPR42600.2020.00080 · DOI
  140. 10.1109/TGRS.2020.2999962 · DOI
  141. 10.1109/CVPR52688.2022.01295 · DOI
  142. 10.1145/3398394 · DOI
  143. 10.24963/ijcai.2022/125 · DOI
  144. kong, 2022, Digital and physical face attacks: Reviewing and one step further, arXiv 2209 14692
  145. 10.1145/3503161.3548171 · DOI
  146. debicha, 2023, Review on the feasibility of adversarial evasion attacks and defenses for network intrusion detection systems, arXiv 2303 07003
  147. 10.1109/CVPR52688.2022.01487 · DOI
  148. 10.1016/j.inffus.2021.02.012 · DOI
  149. 10.1016/j.eswa.2020.114417 · DOI
  150. 10.1109/TPAMI.2020.2974745 · DOI
  151. 10.1016/j.cosrev.2020.100270 · DOI
  152. 10.1109/CVPR52688.2022.01296 · DOI
  153. 10.3390/app9050909 · DOI
  154. 10.1145/2976749.2978392 · DOI · Paper page
  155. 10.1080/00031305.2021.2006781 · DOI
  156. 10.1145/3485133 · DOI
  157. 10.1145/3474085.3475653 · DOI
  158. reza wiyatno, 2019, Adversarial examples in modern machine learning: A review, arXiv 1911 05268
  159. 10.1109/ICCVW54120.2021.00016 · DOI
  160. 10.1109/ICCV48922.2021.00769 · DOI
  161. chakraborty, 2018, Adversarial attacks and defences: A survey, arXiv 1810 00069
  162. 10.1109/CVPRW50498.2020.00415 · DOI
  163. 10.1109/TNNLS.2018.2886017 · DOI · Paper page
  164. 10.1109/CVPR42600.2020.00108 · DOI
  165. wei, 2022, Physical adversarial attack meets computer vision: A decade survey, arXiv 2209 15179
  166. 10.1109/CVPR42600.2020.01426 · DOI
  167. 10.1109/MASSW.2019.00012 · DOI
  168. chen, 2018, ShapeShifter: Robust physical adversarial attack on faster R-CNN object detector, Proc Eur Conf Mach Learn Knowl Discovery Databases, 52
  169. 10.1016/j.procs.2018.10.315 · DOI
  170. song, 2018, Physical adversarial examples for object detectors, Proc 12th USENIX Workshop Offensive Technol (WOOT), 1
  171. wang, 2022, A survey on physical adversarial attack in computer vision, arXiv 2209 14262
  172. 10.1109/CVPR52688.2022.01491 · DOI
  173. 10.1109/CVPR46437.2021.01443 · DOI
  174. 10.1109/ACCESS.2021.3127960 · DOI
  175. 10.1109/CVPR46437.2021.01580 · DOI
  176. 10.1109/ACCESS.2018.2807385 · DOI · Paper page
  177. lovisotto, 2021, SLAP: Improving physical adversarial examples with short-lived adversarial perturbations, Proc USENIX, 1

Cited by

Sorted by citations

Metadata

Authors
Kazmi, S. M. K. A., Aafaq, N., Khan, M. A., Khalil, M., & Saleem, A.
Affiliations
National University of Sciences and Technology (PK)
ORCID
Venue
IEEE Access
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2023
Volume
11
Pages
81256-81278
ISSN
2169-3536 (ISSN-L)
DOI
10.1109/access.2023.3299878
OpenAlex
W4385338774
Cited by
13
References
12
Citations by year
2026: 3 · 2025: 6 · 2024: 2 · 2023: 2
FWCI
1.23
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Access (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National University of Science and Technology (NUST), Islamabad, Pakistan
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
adversarial attacks, aerial imagery, unmanned aerial vehicles, satellite imagery, deep neural network vulnerabilities, adversarial perturbations, physical adversarial attacks, UAV security

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review