Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 180

The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.

Adversarial Machine Learning in Image Classification: A Survey Toward the Defender’s Perspective

Open access
Machado, Gabriel Resende, Silva, Eugênio, Goldschmidt, Ronaldo Ribeiro · 2023 · ACM Computing Surveys

Abstract

Deep Learning algorithms have achieved state-of-the-art performance for Image Classification. For this reason, they have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works have shown those algorithms, which can even surpass human capabilities, are vulnerable to adversarial examples. In Computer Vision, adversarial examples are images containing subtle perturbations generated by malicious optimization algorithms to fool classifiers. As an attempt to mitigate these vulnerabilities, numerous countermeasures have been proposed recently in the literature. However, devising an efficient defense mechanism has proven to be a difficult task, since many approaches demonstrated to be ineffective against adaptive attackers. Thus, this article aims to provide all readerships with a review of the latest research progress on Adversarial Machine Learning in Image Classification, nevertheless, with a defender’s perspective. This article introduces novel taxonomies for categorizing adversarial attacks and defenses, as well as discuss possible reasons regarding the existence of adversarial examples. In addition, relevant guidance is also provided to assist researchers when devising and evaluating defenses. Finally, based on the reviewed literature, this article suggests some promising paths for future research.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3485133

Cites

38 of 38 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 38 references

Research works printed but not linked: 163

  1. Mahdieh Abbasi and Christian Gagné. 2017. Robustness to adversarial examples through an ensemble of specialists. Retrieved from https://arXiv:1702.06856.
  2. 10.1145/3321707.3321749 · DOI · Paper page
  3. Anish Athalye and Nicholas Carlini. 2018. On the robustness of the cvpr 2018 white-box adversarial example defenses. Retrieved from https://arXiv:1804.03286.
  4. Anish Athalye and Ilya Sutskever. 2017. Synthesizing robust adversarial examples. Retrieved from http://arxiv.org/abs/1707.07397. · arXiv
  5. 10.1109/ACCESS.2019.2951526 · DOI
  6. Shumeet Baluja and Ian Fischer. 2017. Adversarial transformation networks: Learning to generate adversarial examples. Retrieved from https://arXiv:1703.09387.
  7. 10.1007/s10994-010-5188-5 · DOI · Paper page
  8. 10.1109/WACV48630.2021.00148 · DOI
  9. Arjun Nitin Bhagoji, Daniel Cullina, and Prateek Mittal. 2017. Dimensionality reduction as a defense against evasion attacks on machine learning classifiers. Retrieved from https://arXiv:1704.02654.
  10. Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhanget al. 2016. End to end learning for self-driving cars. Retrieved from https://arXiv:1604.07316.
  11. Jacob Buckman Aurko Roy Colin Raffel and Ian Goodfellow. 2018. Thermometer encoding: One hot way to resist adversarial examples. In International Conference on Learning Representations .
  12. 10.1145/3134600.3134606 · DOI · Paper page
  13. Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, and Aleksander Madry. 2019. On evaluating adversarial robustness. Retrieved from https://arXiv:1902.06705.
  14. Nicholas Carlini Guy Katz Clark W. Barrett and David L. Dill. 2017. Ground-truth adversarial examples. Retrieved from http://arxiv.org/abs/1709.10207. · arXiv
  15. 10.1145/3128572.3140444 · DOI · Paper page
  16. Nicholas Carlini and David Wagner. 2017. MagNet and “efficient defenses against adversarial attacks” are not robust to adversarial examples. Retrieved from https://arXiv:1711.08478.
  17. 10.1109/SPW.2018.00009 · DOI · Paper page
  18. 10.1007/s11042-018-5853-4 · DOI
  19. Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay. 2018. Adversarial attacks and defences: A survey. Retrieved from https://arXiv:1810.00069.
  20. Jiefeng Chen, Zihang Meng, Changtian Sun, Wei Tang, and Yinglun Zhu. 2017. ReabsNet: Detecting and revising adversarial examples. Retrieved from https://arXiv:1712.08250.
  21. 10.1016/j.cose.2019.04.014 · DOI
  22. 10.5555/3504035.3504037 · doi:10.5555/3504035.3504037
  23. 10.1145/3128572.3140448 · DOI · Paper page
  24. Shang-Tse Chen, Cory Cornelius, Jason Martin, and Duen Horng Polo Chau. 2018. Shapeshifter: Robust physical adversarial attack on faster r-cnn object detector. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 52–68.
  25. Moustapha Cisse, Yossi Adi, Natalia Neverova, and Joseph Keshet. 2017. Houdini: Fooling deep structured prediction models. Retrieved from https://arXiv:1707.05373.
  26. 10.5555/3305381.3305470 · doi:10.5555/3305381.3305470
  27. Gilad Cohen, Guillermo Sapiro, and Raja Giryes. 2019. Detecting adversarial samples using influence functions and nearest neighbors. Retrieved from https://arXiv:1909.06872.
  28. 10.1109/ICASSP.2013.6638293 · DOI · Paper page
  29. Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen, Fred Hohman, Li Chen, Michael E. Kounavis, and Duen Horng Chau. 2017. Keeping the bad guys out: Protecting and vaccinating deep learning with jpeg compression. Retrieved from https://arXiv:1705.02900.
  30. Li Deng. 2012. Three classes of deep learning architectures and their applications: A tutorial survey. APSIPA Trans. Signal Info. Process. 3 (2012), e2. DOI:10.1017/atsip.2013.9 · DOI · Paper page
  31. Guneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton, Jeremy Bernstein, Jean Kossaifi, Aran Khanna, and Anima Anandkumar. 2018. Stochastic activation pruning for robust adversarial defense. Retrieved from https://arXiv:1803.01442.
  32. 10.1016/j.autcon.2017.11.002 · DOI · Paper page
  33. 10.1109/CVPR.2018.00957 · DOI · Paper page
  34. 10.1109/CVPR.2019.00444 · DOI · Paper page
  35. 10.1109/CVPR.2019.00897 · DOI
  36. 10.1109/IJCNN48605.2020.9207596 · DOI
  37. Javid Ebrahimi, Anyi Rao, Daniel Lowd, and Dejing Dou. 2017. Hotflip: White-box adversarial examples for text classification. Retrieved from https://arXiv:1712.06751.
  38. Logan Engstrom, Andrew Ilyas, and Anish Athalye. 2018. Evaluating and understanding the robustness of adversarial logit pairing. Retrieved from https://arXiv:1807.10272.
  39. Ivan Evtimov, Kevin Eykholt, Earlence Fernandes, Tadayoshi Kohno, Bo Li, Atul Prakash, Amir Rahmati, and Dawn Song. 2017. Robust physical-world attacks on deep learning models. In Proceedings of the ACM SIGSAC Conference on Computer and Communications Security. 1528–1540. Retrieved from http://arxiv.org/abs/1707.08945. · arXiv
  40. Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno, and Dawn Song. 2017. Robust physical-world attacks on deep learning models. Retrieved from https://arXiv:1707.08945.
  41. 10.5555/3326943.3327052 · doi:10.5555/3326943.3327052
  42. Alhussein Fawzi, Omar Fawzi, and Pascal Frossard. 2015. Fundamental limits on adversarial robustness. In Proceedings of the ICML Workshop on Deep Learning.
  43. Reuben Feinman Ryan R. Curtin Saurabh Shintre and Andrew B. Gardner. 2017. Detecting adversarial samples from artifacts. Retrieved from http://arxiv.org/abs/1703.00410. · arXiv
  44. Joachim Folz, Sebastian Palacio, Joern Hees, Damian Borth, and Andreas Dengel. 2018. Adversarial defense based on structure-to-signal autoencoders. Retrieved from https://arXiv:1803.07994.
  45. Angus Galloway, Graham W. Taylor, and Medhat Moussa. 2017. Attacking binarized neural networks. Retrieved from https://arXiv:1711.00449.
  46. Ji Gao, Beilun Wang, Zeming Lin, Weilin Xu, and Yanjun Qi. 2017. Deepcloak: Masking deep neural network models for robustness against adversarial samples. Retrieved from https://arXiv:1702.06763.
  47. 10.5555/3153997 · doi:10.5555/3153997
  48. Dave Gershgorn. 2016. Fooling the machine: The byzantine science of deceiving artificial intelligence. Popular Sci. 30 (Mar. 2016).
  49. 10.1609/aaai.v33i01.3301541 · DOI
  50. Justin Gilmer, Luke Metz, Fartash Faghri, Samuel S. Schoenholz, Maithra Raghu, Martin Wattenberg, and Ian Goodfellow. 2018. Adversarial spheres. Retrieved from https://arXiv:1801.02774.
  51. Zhitao Gong, Wenlu Wang, and Wei-Shinn Ku. 2017. Adversarial and clean data are not twins. Retrieved from https://arXiv:1704.04960.
  52. 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
  53. Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Proceedings of the International Conference on Learning Representations. Retrieved from http://arxiv.org/abs/1412.6572. · arXiv
  54. Dou Goodman, Hao Xin, Wang Yang, Wu Yuesheng, Xiong Junfeng, and Zhang Huan. 2020. Advbox: A toolbox to generate adversarial examples that fool neural networks. Retrieved from https://arXiv:2001.05574.
  55. Kathrin Grosse Praveen Manoharan Nicolas Papernot Michael Backes and Patrick McDaniel. 2017. On the (statistical) detection of adversarial examples. Retrieved from http://arxiv.org/abs/1702.06280. · arXiv
  56. 10.1007/978-3-319-66399-9_4 · DOI · Paper page
  57. Shixiang Gu and Luca Rigazio. 2014. Towards deep neural network architectures robust to adversarial examples. Retrieved from http://arxiv.org/abs/1412.5068. · arXiv
  58. Chuan Guo, Mayank Rana, Moustapha Cisse, and Laurens Van Der Maaten. 2017. Countering adversarial images using input transformations. Retrieved from https://arXiv:1711.00117.
  59. 10.1109/SPW.2018.00015 · DOI
  60. 10.1109/CVPR.2016.90 · DOI · Paper page
  61. Warren He Bo Li and Dawn Song. 2018. Decision boundary analysis of adversarial examples. In International Conference on Learning Representations .
  62. 10.5555/3154768.3154783 · doi:10.5555/3154768.3154783
  63. 10.1002/asmb.2209 · DOI · Paper page
  64. Dan Hendrycks and Kevin Gimpel. 2017. Early methods for detecting adversarial images. In Proceedings of the 5th International Conference on Learning Representations (ICLR’17).
  65. 10.1126/science.1127647 · DOI · Paper page
  66. Ruitong Huang, Bing Xu, Dale Schuurmans, and Csaba Szepesvári. 2015. Learning with a strong adversary. Retrieved from https://arXiv:1511.03034.
  67. Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, and Yuan Yao. 2020. Adversarial robustness of stabilized neuralODEs might be from obfuscated gradients. Retrieved from https://arXiv:2009.13145.
  68. Andrew Ilyas, Logan Engstrom, Anish Athalye, and Jessy Lin. 2018. Black-box adversarial attacks with limited queries and information. Retrieved from https://arXiv:1804.08598.
  69. Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry. 2019. Adversarial examples are not bugs, they are features. Retrieved from https://arXiv:1905.02175.
  70. Vishaal Munusamy Kabilan, Brandon Morris, and Anh Nguyen. 2018. VectorDefense: Vectorization as a defense to adversarial examples. Retrieved from https://arXiv:1804.08529.
  71. Harini Kannan, Alexey Kurakin, and Ian Goodfellow. 2018. Adversarial logit pairing. Retrieved from https://arXiv:1803.06373.
  72. Danny Karmon, Daniel Zoran, and Yoav Goldberg. 2018. LaVAN: Localized and visible adversarial noise. Retrieved from https://arXiv:1801.02608.
  73. 10.1145/2994577 · DOI
  74. Erick Knorr. 2015. How paypal beats the bad guys with machine learning. InfoWorld (Apr. 2015). Retrieved from https://www.infoworld.com/article/2907877/machine-learning/how-paypal-reduces-fraud-with-machine-learning.html.
  75. Atul Kumar and Sameep Mehta. 2017. A survey on resilient machine learning. Retrieved from https://arxiv.org/ftp/arxiv/papers/1707/1707.03184.pdf.
  76. 10.1007/978-3-319-94042-7_11 · DOI · Paper page
  77. Alex Lamb Jonathan Binas Anirudh Goyal Dmitriy Serdyuk Sandeep Subramanian Ioannis Mitliagkas and Yoshua Bengio. 2019. Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations. Retrieved from https://openreview.net/forum?id=SkgVRiC9Km.
  78. 10.1007/978-3-030-37337-5_25 · DOI
  79. 10.1109/CVPR42600.2020.00072 · DOI
  80. Xin Li and Fuxin Li. 2016. Adversarial examples detection in deep networks with convolutional filter statistics. Retrieved from https://arXiv:1612.07767.
  81. Xin Li and Fuxin Li. 2016. Adversarial examples detection in deep networks with convolutional filter statistics. Retrieved from https://arxiv.org/abs/1612.07767. · DOI · Paper page
  82. Bin Liang Hongcheng Li Miaoqiang Su Xirong Li Wenchang Shi and Xiaofeng Wang. 2017. Detecting adversarial examples in deep networks with adaptive noise reduction. Retrieved from http://arxiv.org/abs/1705.08378. · arXiv
  83. 10.1109/CVPR.2018.00191 · DOI · Paper page
  84. Ji Lin, Chuang Gan, and Song Han. 2019. Defensive quantization: When efficiency meets robustness. Retrieved from https://arXiv:1904.08444.
  85. 10.1145/3219819.3220027 · DOI
  86. 10.1109/ACCESS.2018.2805680 · DOI · Paper page
  87. Xuanqing Liu, Minhao Cheng, Huan Zhang, and Cho-Jui Hsieh. 2017. Towards robust neural networks via random self-ensemble. Retrieved from https://arXiv:1712.00673.
  88. Xuanqing Liu, Yao Li, Chongruo Wu, and Cho-Jui Hsieh. 2018. ADV-BNN: Improved adversarial defense through robust bayesian neural network. Retrieved from https://arXiv:1810.01279.
  89. Xuanqing Liu, Si Si, Qin Cao, Sanjiv Kumar, and Cho-Jui Hsieh. 2019. Neural SDE: Stabilizing neural ode networks with stochastic noise. Retrieved from https://arXiv:1906.02355.
  90. Zihao Liu, Qi Liu, Tao Liu, Yanzhi Wang, and Wujie Wen. 2018. Feature distillation: DNN-Oriented JPEG compression against adversarial examples. Retrieved from https://arXiv:1803.05787.
  91. 10.1109/ICCV.2017.56 · DOI · Paper page
  92. 10.14722/ndss.2019.23415 · DOI · Paper page
  93. Xingjun Ma, Bo Li, Yisen Wang, Sarah M. Erfani, Sudanthi Wijewickrema, Grant Schoenebeck, Dawn Song, Michael E. Houle, and James Bailey. 2018. Characterizing adversarial subspaces using local intrinsic dimensionality. Retrieved from https://arXiv:1801.02613.
  94. 10.5220/0007714203070318 · doi:10.5220/0007714203070318
  95. 10.1609/aaai.v33i01.33014536 · DOI
  96. 10.1145/3133956.3134057 · DOI · Paper page
  97. Jan Hendrik Metzen, Tim Genewein, Volker Fischer, and Bastian Bischoff. 2017. On detecting adversarial perturbations. Retrieved from https://arXiv:1702.04267.
  98. Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, and Volker Fischer. 2017. Universal adversarial perturbations against semantic image segmentation. Stat 1050(2017), 19.
  99. Takeru Miyato, Andrew M. Dai, and Ian Goodfellow. 2016. Adversarial training methods for semi-supervised text classification. Retrieved from https://arXiv:1605.07725.
  100. Seyed-Mohsen Moosavi-Dezfooli, Ashish Shrivastava, and Oncel Tuzel. 2018. Divide, denoise, and defend against adversarial attacks. Retrieved from https://arXiv:1802.06806.
  101. Aamir Mustafa Salman H. Khan Munawar Hayat Jianbing Shen and Ling Shao. 2019. Image super-resolution as a defense against adversarial attacks. Retrieved from http://arxiv.org/abs/1901.01677. · arXiv
  102. Taesik Na, Jong Hwan Ko, and Saibal Mukhopadhyay. 2017. Cascade adversarial machine learning regularized with a unified embedding. Retrieved from https://arXiv:1708.02582.
  103. 10.1109/CVPRW.2017.172 · DOI · Paper page
  104. Anh Nguyen, Jason Yosinski, and Jeff Clune. 2015. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 427–436. https://doi.org/10.1109/CVPR.2015.7298640arXiv:1412.1897 · doi:10.1109/cvpr.2015.7298640arxiv:1412.1897
  105. Tianyu Pang, Chao Du, and Jun Zhu. 2017. Robust deep learning via reverse cross-entropy training and thresholding test. 3. Retrieved from https://arXiv:1706.00633.
  106. Nicolas Papernot. 2018. A marauder’s map of security and privacy in machine learning. Retrieved from https://arXiv:1811.01134.
  107. Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, and Rujun Long. 2018. Cleverhans v2.1.0: An adversarial machine learning library. Retrieved from https://arXiv:1610.00768.
  108. Nicolas Papernot and Patrick McDaniel. 2017. Extending defensive distillation. Retrieved from http://arxiv.org/abs/1705.05264. · arXiv
  109. Nicolas Papernot and Patrick McDaniel. 2018. Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning. Retrieved from https://arXiv:1803.04765.
  110. 10.1109/SP.2016.41 · DOI · Paper page
  111. 10.1109/CVPR.2018.00894 · DOI · Paper page
  112. Rajeev Ranjan, Swami Sankaranarayanan, Carlos D Castillo, and Rama Chellappa. 2017. Improving network robustness against adversarial attacks with compact convolution. Retrieved from https://arXiv:1712.00699.
  113. Jonas Rauber Wieland Brendel and Matthias Bethge. 2017. Foolbox: A python toolbox to benchmark the robustness of machine learning models. Retrieved from http://arxiv.org/abs/1707.04131. · arXiv
  114. 10.1109/CVPRW.2016.58 · DOI · Paper page
  115. 10.3390/fi10030026 · DOI
  116. 10.1007/s11263-015-0816-y · DOI · Paper page
  117. Pouya Samangouei, Maya Kabkab, and Rama Chellappa. 2018. Defense-gan: Protecting classifiers against adversarial attacks using generative models. Retrieved from https://arXiv:1805.06605.
  118. Sayantan Sarkar, Ankan Bansal, Upal Mahbub, and Rama Chellappa. 2017. UPSET and ANGRI: Breaking high performance image classifiers. Retrieved from https://arXiv:1707.01159.
  119. 10.1016/j.neunet.2014.09.003 · DOI · Paper page
  120. 10.5555/3327345.3327409 · doi:10.5555/3327345.3327409
  121. Sailik Sengupta Tathagata Chakraborti and Subbarao Kambhampati. 2017. MTDeep: Securing deep neural nets against adversarial attacks with moving target defense. Retrieved from http://arxiv.org/abs/1705.07213. · arXiv
  122. Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, and Tom Goldstein. 2018. Are adversarial examples inevitable?Retrieved from https://arXiv:1809.02104.
  123. S. Shen, G. Jin, K. Gao, and Y. Zhang. 2017. APE-GAN: Adversarial perturbation elimination with GAN. Retrieved from https://arXiv:1707.05474.
  124. 10.3390/electronics8060661 · DOI · Paper page
  125. Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. Retrieved from https://arXiv:1409.1556.
  126. Aman Sinha, Hongseok Namkoong, and John Duchi. 2017. Certifying some distributional robustness with principled adversarial training. Retrieved from https://arXiv:1710.10571.
  127. Chawin Sitawarin and David Wagner. 2019. On the robustness of deep k-nearest neighbors. Retrieved from https://arXiv:1903.08333.
  128. Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, and Nate Kushman. 2017. Pixeldefend: Leveraging generative models to understand and defend against adversarial examples. Retrieved from https://arXiv:1710.10766.
  129. Vignesh Srinivasan, Arturo Marban, Klaus-Robert Müller, Wojciech Samek, and Shinichi Nakajima. 2018. Counterstrike: Defending deep learning architectures against adversarial samples by langevin dynamics with supervised denoising autoencoder. Retrieved from https://arXiv:1805.12017.
  130. Shriansh Srivastava, J. Priyadarshini, Sachin Gopal, Sanchay Gupta, and Har Shobhit Dayal. 2019. Optical character recognition on bank cheques using 2D convolution neural network. In Applications of Artificial Intelligence Techniques in Engineering. Springer, 589–596. · DOI
  131. Thilo Strauss, Markus Hanselmann, Andrej Junginger, and Holger Ulmer. 2017. Ensemble methods as a defense to adversarial perturbations against deep neural networks. Retrieved from https://arXiv:1709.03423.
  132. Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15) . 1–9. DOI:10.1109/CVPR.2015.7298594 · DOI · Paper page
  133. Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2818–2826. Retrieved from http://arxiv.org/abs/1512.00567. · arXiv
  134. 10.1109/IJCNN.2016.7727230 · DOI · Paper page
  135. Thomas Tanay and Lewis Griffin. 2016. A boundary tilting perspective on the phenomenon of adversarial examples. Retrieved from https://arXiv:1608.07690.
  136. 10.1109/CVPRW.2019.00012 · DOI · Paper page
  137. Ruben Tolosana, Ruben Vera-Rodriguez, Julian Fierrez, and Javier Ortega-Garcia. 2018. Exploring recurrent neural networks for on-line handwritten signature biometrics. IEEE Access 6, 5128–5138 (2018), 1–7.
  138. Florian Tramèr Alexey Kurakin Nicolas Papernot Dan Boneh and Patrick McDaniel. 2017. Ensemble adversarial training: Attacks and defenses. Retrieved from http://arxiv.org/abs/1705.07204. · arXiv
  139. Florian Tramèr, Nicolas Papernot, Ian Goodfellow, Dan Boneh, and Patrick McDaniel. 2017. The space of transferable adversarial examples. Retrieved from https://arXiv:1704.03453.
  140. 10.5555/3241094.3241142 · doi:10.5555/3241094.3241142
  141. 10.1609/aaai.v33i01.3301742 · DOI · Paper page
  142. Jonathan Uesato, Brendan O’Donoghue, Aaron van den Oord, and Pushmeet Kohli. 2018. Adversarial risk and the dangers of evaluating against weak attacks. Retrieved from https://arXiv:1802.05666.
  143. 10.5555/3276449 · doi:10.5555/3276449
  144. Derui Wang, Chaoran Li, Sheng Wen, Surya Nepal, and Yang Xiang. 2020. Defending against adversarial attack towards deep neural networks via collaborative multi-task training. IEEE Trans. Depend. Secure Comput. (2020), 1–12. DOI:10.1109/TDSC.2020.3014390 · DOI
  145. 10.5555/2671225.2671241 · doi:10.5555/2671225.2671241
  146. 10.1109/ICCV.2019.00673 · DOI
  147. Yizhen Wang and Kamalika Chaudhuri. 2018. Data poisoning attacks against online learning. Retrieved from https://arXiv:1808.08994.
  148. Wenqi Wei, Ling Liu, Margaret Loper, Stacey Truex, Lei Yu, Mehmet Emre Gursoy, and Yanzhao Wu. 2018. Adversarial examples in deep learning: Characterization and divergence. Retrieved from https://arXiv:1807.00051.
  149. Rey Reza Wiyatno, Anqi Xu, Ousmane Dia, and Archy de Berker. 2019. Adversarial examples in modern machine learning: A review. Retrieved from https://arXiv:1911.05268.
  150. 10.5555/3304222.3304312 · doi:10.5555/3304222.3304312
  151. Chaowei Xiao, Jun-Yan Zhu, Bo Li, Warren He, Mingyan Liu, and Dawn Song. 2018. Spatially transformed adversarial examples. Retrieved from https://arXiv:1801.02612.
  152. Huang Xiao. 2017. Adversarial and Secure Machine Learning . Ph.D. Dissertation. Universität München. Retrieved from https://mediatum.ub.tum.de/1335448.
  153. Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, and Alan Yuille. 2017. Mitigating adversarial effects through randomization. Retrieved from https://arXiv:1711.01991.
  154. Boyan Xu, Ruichu Cai, Zhenjie Zhang, Xiaoyan Yang, Zhifeng Hao, Zijian Li, and Zhihao Liang. 2019. NADAQ: Natural language database querying based on deep learning. IEEE Access 7 (2019), 35012–35017. DOI:10.1109/ACCESS.2019.2904720 · DOI
  155. 10.14722/ndss.2018.23198 · DOI · Paper page
  156. Hanshu Yan, Jiawei Du, Vincent Y. F. Tan, and Jiashi Feng. 2019. On robustness of neural ordinary differential equations. Retrieved from https://arXiv:1910.05513.
  157. 10.5555/3326943.3326982 · doi:10.5555/3326943.3326982
  158. Yuzhe Yang, Guo Zhang, Dina Katabi, and Zhi Xu. 2019. ME-Net: Towards effective adversarial robustness with matrix estimation. Retrieved from https://arXiv:1905.11971.
  159. Ziqi Yang, Ee-Chien Chang, and Zhenkai Liang. 2019. Adversarial neural network inversion via auxiliary knowledge alignment. Retrieved from https://arXiv:1902.08552.
  160. 10.1109/SMARTCOMP.2017.7946998 · DOI · Paper page
  161. 10.1145/3128572.3140449 · DOI · Paper page
  162. 10.1007/978-3-319-10590-1_53 · DOI · Paper page
  163. 10.5555/3327757.3327888 · doi:10.5555/3327757.3327888

Cited by

See all 180

Metadata

Authors
Machado, G. R., Silva, E., & Goldschmidt, R. R.
Venue
ACM Computing Surveys
Published
2021-11-23
Volume
55
Issue
1
Pages
1-38
ISSN
  • 0360-0300 (ISSN-L)
  • 1557-7341
OpenAlex
W3216686652
Cited by
180
References
38
FWCI
11.38
Type
journal article
Language
en
Open access
green

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Adversarial Machine Learning in Image Classification: A Survey Toward the Defender’s Perspective. https://app.cochat.ai/papers/10.1145/3485133
The paper
Machado, G. R., Silva, E., & Goldschmidt, R. R. (2023). Adversarial Machine Learning in Image Classification: A Survey Toward the Defender’s Perspective. ACM Computing Surveys. https://doi.org/10.1145/3485133

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.