CoChat
Sign Up
Cited by 90Adversarial Robustness in Machine LearningPrivacy-Preserving Technologies in DataDigital Media Forensic Detection

Adversarial Attacks Against Deep Generative Models on Data: A Survey

Open access
Sun, Hui, Zhu, Tianqing, Zhang, Zhiqiu, Jin, Dawei, Xiong, Ping, Zhou, Wanlei·2023·IEEE Transactions on Knowledge and Data Engineering
DOI 10.1109/tkde.2021.3130903
Open this paper in CoChat — free accountOpen PDF

Abstract

Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial networks (GANs) and variational auto-encoders (VAEs). Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. In fact, these models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/VAEs, the discriminators/encoders of GANs/VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field.

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/tkde.2021.3130903

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

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?

  • A study addresses the vulnerabilities of generative models to adversarial attacks, such as evasion attacks and membership inference attacks, highlighting a significant area of concern in health care data security.

    “Finally, a study addresses the vulnerabilities of generative models to adversarial attacks (eg, evasion attacks and membership inference attacks), highlighting a significant area of concern in health care data security [51].”

    From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [51]

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 108

  1. T. Karras, T. Aila, S. Laine, and J. Lehtinen, "Progressive growing of GANs for improved quality, stability, and variation," in Proc. Int. Conf. Learn. Representations, 2018.
  2. I. Masi, Y. Wu, T. Hassner, and P. Natarajan, "Deep Face Recog- nition: A Survey," in Proc. Conf. Graph., Patterns Images, 2018, pp. 471-478.
  3. T. Jebara, Machine Learning: Discriminative and Generative, Kluwer, vol. 755, no. SECS 755, 2004.
  4. I. Goodfellow et al., "Generative adversarial nets," in Proc. Conf. Neural Inform. Process. Syst., vol. 27, 2014, pp. 2672-2680.
  5. D. P. Kingma and M. Welling, "Auto-encoding variational bayes," in Proc. Int. Conf. Learn. Representations, 2014.
  6. C. Vondrick, H. Pirsiavash, and A. Torralba, "Generating videos with scene dynamics," in Proc. Conf. Neural Inform. Process. Syst., 2016, pp. 613-621.
  7. P. Isola, J. Zhu, T. Zhou, and A. A. Efros, "Image-to-image trans- lation with conditional adversarial networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 5967-5976.
  8. W. Medhat, A. Hassan, and H. Korashy, "Sentiment analysis algo- rithms and applications: A survey," Ain Shams Eng. J., vol. 5, no. 4, pp. 1093-1113, 2014.
  9. L. Deng, Y. Liu, Deep Learning in Natural Language Processing, Berlin, Germany: Springer, 2018.
  10. J. Hirschberg and C. D. Manning, "Advances in natural language processing," Science, vol. 349, no. 6245, pp. 261-266, 2015.
  11. D. Pasquini M. Mingione, M. Bernaschi, "Adversarial out- domain examples for generative models", in Proc. IEEE Eur. Symp. Secur. Privacy, 2019, pp.272-280.
  12. F. Tram er, F. Zhang, A. Juels, M. K. Reiter, and T. Ristenpart, "Stealing machine learning models via prediction APIs," in Proc. USENIX Conf. Secur. Symp., 2016, pp. 601-618.
  13. M. Fredrikson, S. Jha, and T. Ristenpart, "Model inversion attacks that exploit confidence information and basic counter- measures," in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., 2015, pp. 1322-1333.
  14. M. Barreno, B. Nelson, A. D. Joseph, and J. D. Tygar, "The secu- rity of machine learning," Mach. Learn., vol. 81, no. 2, pp. 121- 148, 2010.
  15. N. Papernot, P. D. McDaniel, A. Sinha, and M. P. Wellman, "Towards the science of security and privacy in machine learning," 2016, arXiv:1611.03814v1. · arXiv
  16. B. Biggio et al., "Evasion attacks against machine learning at test time," in Proc. Eur. Conf. Mach. Learn. Princ. Pract. Knowl. Discov. Databases, 2013, pp. 387-402.
  17. J. Jia, B. Wang, L. Zhang, and N. Z. Gong, "Attriinfer: Inferring user attributes in online social networks using Markov random fields," in Proc. 26th Int. Conf. World Wide Web, 2017, pp. 1561-1569.
  18. N. Papernot, P. D. McDaniel, A. Sinha, and M. P. Wellman, "SoK: Security and privacy in machine learning," in Proc. IEEE Eur. Symp. Secur. Privacy, 2018, pp. 399-414.
  19. B. Liu, M. Ding, S. Shaham, W. Rahayu, F. Farokhi, and Z. Lin, "When machine learning meets privacy: A survey and outlook," ACM Comput. Surv., vol. 54, no. 2, pp. 31:1-31:36, 2021.
  20. A. C. Serban, E. Poll, and J. Visser, "Adversarial examples on object recognition: A comprehensive survey," ACM Comput. Surv., vol. 53, no. 3, pp. 66:1-66:38, 2020.
  21. M. Gong, Y. Xie, K. Pan, K. Feng, and A. K. Qin, "A survey on differentially private machine learning," IEEE Comput. Intell. Mag., vol. 15, no. 2, pp. 49-64, May 2020.
  22. G. Litjens et al., "A survey on deep learning in medical image analysis," Med. Image Anal., vol. 42, pp. 60-88, 2017.
  23. W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F. E. Alsaadi, "A survey of deep neural network architectures and their applications," Neuro- computing, vol. 234, pp. 11-26, 2017.
  24. Q. Zhang, L. T. Yang, Z. Chen, and P. Li, "A survey on deep learning for big data," Inf. Fusion, vol. 42, pp. 146-157, 2018.
  25. A. Kamilaris and F. X. Prenafeta-Boldu, "Deep learning in agri- culture: A survey," Comput. Electron. Agriculture., vol. 147, pp. 70-90, 2018.
  26. Z. Zhang, P. Cui, and W. Zhu, "Deep learning on graphs: A survey," 2018, arXiv:1812.04202v3. · arXiv
  27. S. Ding, Y. Tian, F. Xu, Q. Li, and S. Zhong, "Trojan attack on deep generative models in autonomous driving," in Proc. Int. Conf. Secur. Privacy Commun. Syst., 2019, pp. 299-318
  28. A. Salem, Y. Sautter, M. Backes, M. Humbert, and Y. Zhang, "BAAAN: Backdoor attacks against autoencoder and GAN- based machine learning models," 2020, arXiv:2010.03007v2. · arXiv
  29. G. Gondim-Ribeiro, P. Tabacof, and E. Valle, "Adversarial attacks on variational autoencoders," 2018, arXiv:1806.04646v1. · arXiv
  30. J. Kos, I. Fischer, and D. Song, "Adversarial examples for genera- tive models," in Proc. IEEE Symp. Secur. Privacy Workshops, 2018, pp. 36-42.
  31. P. Tabacof, J. Tavares, and E. Valle, "Adversarial images for vari- ational autoencoders," 2016, arXiv:1612.00155v1. · arXiv
  32. C. Yeh, H. Chen, S. Tsai, and S. Wang, "Disrupting image- translation-based deepfake algorithms with adversarial attacks," in Proc. IEEE Winter Appl. Comput. Vis. Workshop, 2020, pp. 53-62.
  33. C. Sun, S. Chen, J. Cai, and X. Huang, "Type I attack for gen- erative models," in Proc. IEEE Int. Conf. Image Process., 2020, pp. 593-597.
  34. C. Yang, L. Zhou, H. Wen, and Y. Wu, "U-ASG: A universal method to perform adversarial attack on autoencoder based net- work anomaly detection systems," in Proc. IEEE Conf. Comput. Commun. Workshops, 2020, pp. 68-73.
  35. O. Mendelevitch and M. D. Lesh, "Fidelity and privacy of syn- thetic medical data," 2021, arXiv:2101.08658v2. · arXiv
  36. D. Chen, N. Yu, Y. Zhang, and M. Fritz, "GAN-Leaks: A taxonomy of membership inference attacks against generative models," in Proc. Annu. ACM Comput. Commun. Secur. Conf., 2020, pp. 343- 362.
  37. B. Hilprecht, M. H€ arterich, and D. Bernau, "Monte carlo and reconstruction membership inference attacks against generative models," Proc. Privacy Enhancing Technol., vol. 2019, no. 4, pp. 232-249, 2019.
  38. K. S. Liu, C. Xiao, B. Li, and J. Gao, "Performing co-membership attacks against deep generative models," in Proc. IEEE Int. Conf. Data Mining, 2019, pp. 459-467.
  39. T. Stadler, B. Oprisanu, and C. Troncoso, "Synthetic data -A pri- vacy mirage," 2020, arXiv:2011.07018v5. · arXiv
  40. H. Hu and J. Pang, "Model extraction and defenses on generative adversarial networks," 2021, arXiv:2101.02069v1. · arXiv
  41. I. Higgins et al., "beta-VAE: Learning basic visual concepts with a constrained variational framework," in Proc. Int. Conf. Learn. Repre- sentations, 2017.
  42. M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein generative adversarial networks," in Proc. Int. Conf. Mach. Learn., 2017, vol. 70, pp. 214-223.
  43. A. Oussidi, A. Elhassouny, "Deep generative models: Survey,", in Proc. Int. Conf. Intell. Syst. Comput. Vis., 2018, pp. 1-8.
  44. R. B. Myerson, Game Theory -Analysis of Conflict. Harvard Univ. Press, 1997.
  45. X. Chen, C. Liu, B. Li, K. Lu, and D. Song, "Targeted backdoor attacks on deep learning systems using data poisoning," 2017, arXiv:1712.05526v1. · arXiv
  46. C. Li, H. Shirani-Mehr, and X. Yang, "Protecting individual infor- mation against inference attacks in data publishing," in Proc. Int. Conf. Database Syst. Adv. Appl., 2007, vol. 4443, pp. 422-433.
  47. Y. Shen, J. Gu, X. Tang, and B. Zhou, "Interpreting the latent space of GANs for semantic face editing," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2020, pp. 9240-9249.
  48. A. Pati and A. Lerch, "Attribute-based regularization of latent spaces for variational auto-encoders," Neural Comput. Appl., vol. 33, no. 9, pp. 4429-4444, 2021.
  49. S. Samonas and D. Coss, "The CIA strikes back: Redefining confi- dentiality, integrity and availability in security," J. Inf. Syst. Secur., vol. 10, no. 3, pp. 21-45, 2014.
  50. A. Goncalves, P. Ray, B. Soper, J. Stevens, L. Coyle, and A. P. Sales, "Generation and evaluation of synthetic patient data," vol. 20, no. 1, 2020, Art. no. 108.
  51. A. B. L. Larsen, S. K. Sønderby, H. Larochelle, and O. Winther, "Autoencoding beyond pixels using a learned similarity metric," in Proc. Int. Conf. Mach. Learn., 2016, vol. 48, pp. 1558-1566.
  52. B. Biggio, B. Nelson, and P. Laskov, "Poisoning attacks against support vector machines," in Proc. Int. Conf. Mach. Learn., 2012.
  53. A. Shafahi et al., "Poison frogs! Targeted clean-label poisoning attacks on neural networks," in Proc. Conf. Neural Inform. Process. Syst., 2018, pp. 6106-6116.
  54. S. Alfeld, X. Zhu, and P. Barford, "Data poisoning attacks against autoregressive models," in Proc. of AAAI Conf. Artif. Intell., 2016, pp. 1452-1458.
  55. C. Yang, Q. Wu, H. Li, and Y. Chen, "Generative poisoning attack method against neural networks," 2017, arXiv:1703.01340v1. · arXiv
  56. T. Salimans and D. P. Kingma, "Weight normalization: A simple reparameterization to accelerate training of deep neural networks," in Proc. Conf. Neural Inform. Process. Syst., 2016, Art. no. 901.
  57. N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Sala- khutdinov, "Dropout: A simple way to prevent neural networks from overfitting," J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929-1958, 2014.
  58. B. K. Beaulieu-Jones et al., "Privacy-preserving generative deep neural networks support clinical data sharing," Circulation: Car- diovascular Quality Outcomes, vol. 12, no. 7, 2019, Art. no. e005122.
  59. J. Hayes, L. Melis, G. Danezis, and E. D. Cristofaro, "LOGAN: Evaluating privacy leakage of generative models using genera- tive adversarial networks," 2017, arXiv:1705.07663v4. · arXiv
  60. X. Zhang, S. Ji, and T. Wang, "Differentially private releasing via deep generative model," 2018, arXiv:1801.01594v2. · arXiv
  61. L. Xie, K. Lin, S. Wang, F. Wang, and J. Zhou, "Differentially pri- vate generative adversarial network," 2018, arXiv:1802.06739v1. · arXiv
  62. C. Dwork and A. Roth, "The algorithmic foundations of differen- tial privacy," Found. TrendsircledR Theor. Comput. Sci., vol. 9, no. 3-4, pp. 211-407, 2014.
  63. D. Chen, T. Orekondy, and M. Fritz, "GS-WGAN: A gradient- sanitized approach for learning differentially private gener- ators," in Proc. Conf. Neural Inform. Process. Syst., 2020.
  64. R. Torkzadehmahani, P. Kairouz, and B. Paten, "DP-CGAN: Dif- ferentially private synthetic data and label generation," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops, 2019, pp. 98-104.
  65. M. Mirza and S. Osindero, "Conditional generative adversarial nets," 2014, arXiv:1411.1784v1. · arXiv
  66. I. Mironov, "Renyi differential privacy," in Proc. IEEE 34th Com- put. Secur. Found. Symp., 2017, pp. 263-275.
  67. C. Sun, S. Chen, and X. Huang, "Double backpropagation for training autoencoders against adversarial attack," 2020, arXiv:2003.01895v1. · arXiv
  68. M. Willetts, A. Camuto, T. Rainforth, S. J. Roberts, and C. C. Holmes, "Improving vaes' robustness to adversarial attack," in Proc. Int. Conf. Learn. Representations, 2021.
  69. K. Liu, B. Dolan-Gavitt, and S. Garg, "Fine-pruning: Defending against backdooring attacks on deep neural networks," in Proc. Int. Symp. Res. Attacks, Intrusions Defenses, 2018, vol. 11050, pp. 273-294.
  70. S. Mukherjee, Y. Xu, A. Trivedi, N. Patowary, and J. L. Ferres, "privGAN: Protecting GANs from membership inference attacks at low cost to utility," Proc. Priv. Enhancing Technol., vol. 2021, no. 3, pp. 142-163, 2021.
  71. G. G. Chrysos, J. Kossaifi, and S. Zafeiriou, "RoCGAN: Robust con- ditional GAN," Int. J. Comput. Vis., vol. 128, no. 10, pp. 2665-2683, 2020.
  72. L. Tran, J. Kossaifi, Y. Panagakis, and M. Pantic, "Disentangling geometry and appearance with regularised geometry-aware gener- ative adversarial networks," Int. J. Comput. Vis., vol. 127, no. 6-7, 2019, pp. 824-844.
  73. J. Jordon, J. Yoon, and M. van der Schaar, "PATE-GAN: Generat- ing synthetic data with differential privacy guarantees," in Proc. Int. Conf. Learn. Representations, 2019.
  74. D. S. Ong, C. S. Chan, K. Ng, L. Fan, and Q. Yang, "Protecting intellectual property of generative adversarial networks from ambiguity attack," 2021, arXiv:2102.04362v2. · arXiv
  75. L. Fan, K. Ng, and C. S. Chan, "Rethinking deep neural network ownership verification: Embedding passports to defeat ambigu- ity attacks," in Proc. Conf. Neural Inform. Process. Syst., 2019.
  76. B. Tran, J. Li, and A. Madry, "Spectral signatures in backdoor attacks," in Proc. Conf. Neural Inform. Process. Syst., 2018, pp. 8011-8021.
  77. B. Chen et al., "Detecting backdoor attacks on deep neural net- works by activation clustering," in Proc. Workshop AAAI Conf. Artif. Intell., vol. 2301, 2019.
  78. Z. Katzir and Y. Elovici, "Detecting adversarial perturbations through spatial behavior in activation spaces," in Proc. Int. Joint Conf. Neural Netw., 2019, pp. 1-9.
  79. A. S. Rakin, J. Yi, B. Gong, and D. Fan, "Defend deep neural net- works against adversarial examples via fixed and dynamic quan- tized activation functions," 2018, arXiv:1807.06714. · arXiv
  80. L. Perez and J. Wang, "The effectiveness of data augmentation in image classification using deep learning,", 2017, arXiv:1712.04621v1. · arXiv
  81. Y. Zeng, H. Qiu, G. Memmi, and M. Qiu, "A data augmentation- based defense method against adversarial attacks in neural networks," in Proc. Int. Workshops Symp. Algorithms Archit. Paral- lel Process., vol. 12453, 2020, pp. 274-289.
  82. E. Borgnia et al., "Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff," in Proc. IEEE Int. Conf. Acoust., Speech Signal Process., 2021, pp. 3855-3859.
  83. Y. Cai et al., "Dualattn-GAN: Text to image synthesis with dual attentional generative adversarial network," IEEE Access, vol. 7, pp. 183 706-183 716, 2019.
  84. H. Zhang et al., "StackGAN++: Realistic image synthesis with stacked generative adversarial networks," IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 8, pp. 1947-1962, Aug. 2019.
  85. J. Li, W. Monroe, T. Shi, S. Jean, A. Ritter, and D. Jurafsky, "Adversarial learning for neural dialogue generation," in Proc. Conf. Empirical Methods Nat. Lang. Process., 2017, pp. 2157-2169.
  86. Y. Li, Q. Pan, S. Wang, T. Yang, and E. Cambria, "A Generative Model for category text generation," Inf. Sci., vol. 450, pp. 301- 315, 2018.
  87. A. Saeed, S. Ilic, and E. Zangerle, "Creative GANs for generating poems, lyrics, and metaphors," 2019, arXiv:1909.09534v1. · arXiv
  88. E. Choi, S. Biswal, B. A. Malin, J. Duke, W. F. Stewart, and J. Sun, "Generating multi-label discrete patient records using generative adversarial networks," in Proc. Mach. Learn. Healthcare, vol. 68, 2017, pp. 286-305.
  89. B. Liang, H. Li, M. Su, P. Bian, X. Li, and W. Shi, "Deep text clas- sification can be fooled," in Proc. Int. Joint Conf. Artif. Intell., 2018, pp. 4208-4215.
  90. N. Papernot, P. D. McDaniel, A. Swami, and R. E. Harang, "Crafting adversarial input sequences for recurrent neural networks," IEEE Military Commun. Conf., 2016, pp. 49-54.
  91. M. Alzantot, Y. Sharma, A. Elgohary, B.-J. Ho, M. B. Srivastava, and K.-W. Chang, "Generating natural language adversarial examples," in Proc. Conf. Empirical Methods Nat. Lang. Process., 2018, pp. 2890-2896.
  92. D. Pruthi, B. Dhingra, and Z. C. Lipton, "Combating adversarial misspellings with robust word recognition," in Proc. Annu. Meet- ing Assoc. Comput. Linguistics, 2019, pp. 5582-5591.
  93. T. B. Brown, D. Mane, A. Roy, M. Abadi, and J. Gilmer, "Adversarial patch," 2017, arXiv:1712.09665v2. · arXiv
  94. C. Szegedy et al., "Intriguing properties of neural networks," in Proc. of Int. Conf. Learn. Representations, 2014.
  95. S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard, "DeepFool: A simple and accurate method to fool deep neural networks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 2574-2582.
  96. X. Liu, H. Yang, Z. Liu, L. Song, Y. Chen, and H. Li, "DPATCH: An adversarial patch attack on object detectors," in Proc. AAAI Conf. Artif. Intell., 2019, vol. 2301
  97. J. Redmon and A. Farhadi, "YOLO9000: Better, faster, stronger," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 6517-6525.
  98. Y. Zhao, H. Yan, and X. Wei, "Object hider: Adversarial patch attack against object detectors," 2020, arXiv:2010.14974v1. · arXiv
  99. T. ZhuG. LiW. Zhou, P. S. Yu, "Differentially private data pub- lishing and analysis: A survey,", IEEE Trans. Knowl Data Eng., vol. 29, no. 8, pp. 1619-1638, Aug. 2017.
  100. H. B. McMahan and G. Andrew, "A general approach to adding differential privacy to iterative training procedures," 2018, arXiv:1812.06210v2. · arXiv
  101. P. Subramani, N. Vadivelu, and G. Kamath, "Enabling fast differen- tially private SGD via just-in-time compilation and vectorization," 2020, arXiv:2010.09063v2. · arXiv
  102. S. Mukherjee, Y. Xu, A. Trivedi, N. Patowary, and J. L. Ferres, "privGAN: Protecting gans from membership inference attacks at low cost to utility," Proc. Privacy Enhancing Technol., vol. 2021, no. 3, pp. 142-163, 2021.
  103. L. ZhangT. ZhuP. XiongW. Zhou, P. S. Yu, "More than privacy: Adopting differential privacy in game-theoretic mechanism design", ACM Comput. Surv., pp. 5471-37, Jul. 2021.
  104. "MD-GAN: Multi-discriminator generative adversarial networks for distributed datasets," in Proc. IEEE Int. Parallel Distrib. Pro- cess. Symp., 2019, pp. 866-877.
  105. M. Rasouli, T. Sun, and R. Rajagopal, "Fedgan: Federated generative adversarial networks for distributed data," 2020, arXiv:2006.07228v2. · arXiv
  106. R. A. and N. V., "Federated AI lets a team imagine together: Fed- erated learning of GANs," 2019, arXiv:1906.03595v1. · arXiv
  107. Y. Zhang, H. Qu, Q. Chang, H. Liu, D. N. Metaxas, and C. Chen, "Training federated GANs with theoretical guarantees: A uni- versal aggregation approach," 2021, arXiv:2102.04655v1. · arXiv
  108. J. Rajotte et al., "Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary," in Proc. Conf. Inf. Technol. Social Good, 2021, pp. 79-84.

Cited by

Sorted by citations

Authors
Sun, H., Zhu, T., Zhang, Z., Jin, D., Xiong, P., & Zhou, W.
Affiliations
  • China University of Geosciences (CN)
  • Zhongnan University of Economics and Law (CN)
  • City University of Macau (MO)
ORCID
Venue
IEEE Transactions on Knowledge and Data Engineering
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2023-04-01
Volume
35
Issue
4
Pages
3367-3388
ISSN
  • 1041-4347 (ISSN-L)
  • 1558-2191
  • 2326-3865
DOI
10.1109/tkde.2021.3130903
OpenAlex
W3216683580
Cited by
90
References
16
Citations by year
2026: 16 · 2025: 35 · 2024: 23 · 2023: 8 · 2022: 8
FWCI
3.45
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Knowledge and Data Engineering (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Natural Science Foundation of China (61972366)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
Keywords
adversarial attacks, deep generative models, generative adversarial networks, variational autoencoder, security threats, privacy preservation, defense strategy

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