CoChat
Sign Up
Cited by 445Privacy-Preserving Technologies in DataCloud Data Security SolutionsPrivacy, Security, and Data Protection

Differential Privacy for Deep and Federated Learning: A Survey

Open access
Ouadrhiri, Ahmed El, Abdelhadi, Ahmed·2022·IEEE Access
DOI 10.1109/access.2022.3151670
Open this paper in CoChat — free accountOpen PDF

Abstract

Users’ privacy is vulnerable at all stages of the deep learning process. Sensitive information of users may be disclosed during data collection, during training, or even after releasing the trained learning model. Differential privacy (DP) is one of the main approaches proven to ensure strong privacy protection in data analysis. DP protects the users’ privacy by adding noise to the original dataset or the learning parameters. Thus, an attacker could not retrieve the sensitive information of an individual involved in the training dataset. In this survey paper, we analyze and present the main ideas based on DP to guarantee users’ privacy in deep and federated learning. In addition, we illustrate all types of probability distributions that satisfy the DP mechanism, with their properties and use cases. Furthermore, we bridge the gap in the literature by providing a comprehensive overview of the different variants of DP, highlighting their advantages and limitations. Our study reveals the gap between theory and application, accuracy, and robustness of DP. Finally, we provide several open problems and future research directions.

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/access.2022.3151670

Cites

9 of 9 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?

  • There are studies that focus on specific PPML techniques such as DP for cyber-physical systems, privacy preservation in blockchain-based IoT, DP in deep-FL, and HE and SMPC for secure PPML computation.

    “Besides broader survey studies, there are studies that focus on specific PPML techniques such as DP techniques for cyber-physical systems [48], privacy preservation in blockchain-based IoT systems [49], DP in deep-FL [28], and HE [109] and SMPC [184] for secure PPML computation.”

    From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [28]

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: 127

  1. M. M. Islam, F. Karray, R. Alhajj, and J. Zeng, ''A review on deep learning techniques for the diagnosis of novel coronavirus (COVID-19),'' IEEE Access, vol. 9, pp. 30551-30572, 2021.
  2. F. Xing, Y. Xie, H. Su, F. Liu, and L. Yang, ''Deep learning in microscopy image analysis: A survey,'' IEEE Trans. Neural Netw. Learn. Syst., vol. 29, no. 10, pp. 4550-4568, Oct. 2018.
  3. A. Yahyaoui, A. Jamil, J. Rasheed, and M. Yesiltepe, ''A decision support system for diabetes prediction using machine learning and deep learning techniques,'' in Proc. 1st Int. Informat. Softw. Eng. Conf. (UBMYK), Nov. 2019, pp. 1-4.
  4. S. Blaziunas and A. Raudys, ''Comparative study of neural networks and decision trees for application in trading financial futures,'' in Proc. Int. Conf. Deep Learn. Mach. Learn. Emerg. Appl. (Deep-ML), Aug. 2019, pp. 33-38.
  5. M. Nabipour, P. Nayyeri, H. Jabani, S. Shahab, and A. Mosavi, ''Pre- dicting stock market trends using machine learning and deep learning algorithms via continuous and binary data; a comparative analysis,'' IEEE Access, vol. 8, pp. 150199-150212, 2020.
  6. K.-C. Chen, H.-W. Yeh, J.-Y. Hang, S.-H. Jhang, W.-Z. Zheng, and Y.-H. Lai, ''A joint-feature learning-based voice conversion system for dysarthric user based on deep learning technology,'' in Proc. 41st Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Jul. 2019, pp. 1838-1841.
  7. X. Fei, F. Long, F. Li, and Q. Ling, ''Multi-component fusion temporal networks to predict vehicle exhaust based on remote monitoring data,'' IEEE Access, vol. 9, pp. 42358-42369, 2021.
  8. J. H. Abawajy, M. I. H. Ninggal, and T. Herawan, ''Privacy preserving social Network data publication,'' IEEE Commun. Surveys Tuts., vol. 18, no. 3, pp. 1974-1997, 3rd Quart., 2016.
  9. H. Ren, J. Deng, and X. Xie, ''GRNN: Generative regression neural network-A data leakage attack for federated learning,'' CoRR, New York, NY, USA, Tech. Rep. 2105.00529, 2021.
  10. J. Zhao, Y. Chen, and W. Zhang, ''Differential privacy preservation in deep learning: Challenges, opportunities and solutions,'' IEEE Access, vol. 7, pp. 48901-48911, 2019.
  11. L. Sweeney, ''K-anonymity: A model for protecting privacy,'' Int. J. Uncertainty, Fuzziness Knowl.-Based Syst., vol. 10, no. 5, pp. 557-570, 2002, doi: 10.1142/S0218488502001648. · DOI · Paper page
  12. C. C. Aggarwal, ''On k-anonymity and the curse of dimensionality,'' in Proc. 31st Int. Conf. Very Large Data Bases (VLDB), 2005, pp. 901-909.
  13. J. Brickell and V. Shmatikov, ''The cost of privacy: Destruction of data-mining utility in anonymized data publishing,'' in Proc. 14th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining (KDD), 2008, pp. 70-78, doi: 10.1145/1401890.1401904. · DOI
  14. A. Machanavajjhala, J. Gehrke, D. Kifer, and M. Venkitasubramaniam, ''L-diversity: Privacy beyond k-anonymity,'' in Proc. 22nd Int. Conf. Data Eng. (ICDE), 2006, p. 24.
  15. Y. Rubner, C. Tomasi, and L. J. Guibas, ''The earth mover's distance as a metric for image retrieval,'' Int. J. Comput. Vis., vol. 40, no. 2, pp. 99-121, Nov. 2000, doi: 10.1023/A:1026543900054. · DOI
  16. R. Canetti, ''Security and composition of multiparty cryptographic protocols,'' J. Cryptol., vol. 13, no. 1, pp. 143-202, Jan. 2000, doi: 10.1007/s001459910006. · DOI
  17. S. Sayyad, ''Privacy preserving deep learning using secure multiparty computation,'' in Proc. 2nd Int. Conf. Inventive Res. Comput. Appl. (ICIRCA), Jul. 2020, pp. 139-142.
  18. R. Shokri and V. Shmatikov, ''Privacy-preserving deep learning,'' in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., Oct. 2015, pp. 1310-1321, doi: 10.1145/2810103.2813687. · DOI · Paper page
  19. K. Bonawitz, V. Ivanov, B. Kreuter, A. Marcedone, H. B. McMahan, S. Patel, D. Ramage, A. Segal, and K. Seth, ''Practical secure aggregation for privacy-preserving machine learning,'' in Proc. ACM SIGSAC Conf. Comput. Commun. Secur., Oct. 2017, pp. 1175-1191, doi: 10.1145/3133956.3133982. · DOI · Paper page
  20. C. Gentry, ''Fully homomorphic encryption using ideal lattices,'' in Proc. 41st Annu. ACM Symp. Symp. Theory Comput. (STOC), 2009, pp. 169-178, doi: 10.1145/1536414.1536440. · DOI · Paper page
  21. P. Li, J. Li, Z. Huang, T. Li, C.-Z. Gao, S.-M. Yiu, and K. Chen, ''Multi- key privacy-preserving deep learning in cloud computing,'' Future Gen- erat. Comput. Syst. vol. 74, pp. 76-85, Sep. 2017.
  22. L. T. Phong, Y. Aono, T. Hayashi, L. Wang, and S. Moriai, ''Privacy- preserving deep learning via additively homomorphic encryption,'' IEEE Trans. Inf. Forensics Security, vol. 13, no. 5, pp. 1333-1345, May 2018.
  23. Q. Zhu and X. Lv, ''2P-DNN: Privacy-preserving deep neural networks based on homomorphic cryptosystem,'' 2018, arXiv:1807.08459. · arXiv
  24. Q. Zhang, L. T. Yang, and Z. Chen, ''Privacy preserving deep computation model on cloud for big data feature learning,'' IEEE Trans. Comput., vol. 65, no. 5, pp. 1351-1362, May 2016.
  25. C. Dwork, F. McSherry, K. Nissim, and A. Smith, ''Calibrating noise to sensitivity in private data analysis,'' in Proc. 3rd Conf. Theory Cryptogr., Berlin, Germany: Springer, 2006, pp. 265-284.
  26. C. Dwork, ''Differential privacy: A survey of results,'' in Theory and Applications of Models of Computation, M. Agrawal, D. Du, Z. Duan, and A. Li, Eds. Berlin, Germany: Springer, 2008, pp. 1-19.
  27. M. Kim, O. Gunlu, and R. F. Schaefer, ''Federated learning with local differential privacy: Trade-offs between privacy, utility, and communica- tion,'' in Proc. ICASSP -IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), Jun. 2021, pp. 2650-2654.
  28. X. Ding, C. Wang, K.-K. Raymond Choo, and H. Jin, ''A novel privacy preserving framework for large scale graph data publishing,'' IEEE Trans. Knowl. Data Eng., vol. 33, no. 2, pp. 331-343, Feb. 2021.
  29. B. Zhao, K. Fan, K. Yang, Z. Wang, H. Li, and Y. Yang, ''Anonymous and privacy-preserving federated learning with industrial big data,'' IEEE Trans. Ind. Informat., vol. 17, no. 9, pp. 6314-6323, Sep. 2021.
  30. S. P. Kasiviswanathan, H. K. Lee, K. Nissim, S. Raskhodnikova, and A. Smith, ''What can we learn privately?'' in Proc. 49th Annu. IEEE Symp. Found. Comput. Sci., Oct. 2008, pp. 793-826.
  31. A. Evfimievski, J. Gehrke, and R. Srikant, ''Limiting privacy breaches in privacy preserving data mining,'' in Proc. 22nd ACM SIGMOD-SIGACT- SIGART Symp. Princ. Database Syst. (PODS), 2003, pp. 211-222, doi: 10.1145/773153.773174. · DOI
  32. R. Bassily, K. Nissim, U. Stemmer, and A. Thakurta, ''Practi- cal locally private heavy hitters,'' CoRR, New York, NY, USA, Tech. Rep. 1707.04982, 2017.
  33. T. Ha, T. K. Dang, T. T. Dang, T. A. Truong, and M. T. Nguyen, ''Dif- ferential privacy in deep learning: An overview,'' in Proc. Int. Conf. Adv. Comput. Appl. (ACOMP), Nov. 2019, pp. 97-102.
  34. H. Dong, C. Wu, Z. Wei, and Y. Guo, ''Dropping activation outputs with localized first-layer deep network for enhancing user privacy and data security,'' IEEE Trans. Inf. Forensics Security, vol. 13, no. 3, pp. 662-670, Mar. 2018.
  35. N. Papernot, M. Abadi, E. rlingsson. Ú., I. Goodfellow, and K. Talwar, ''Semi-supervised knowledge transfer for deep learning from private training data,'' arXiv, New York, NY, USA, Tech. Rep. 1610.05755, 2017.
  36. L. T. Phong, Y. Aono, T. Hayashi, L. Wang, and S. Moriai, ''Privacy- preserving deep learning: Revisited and enhanced,'' in Applications and Techniques in Information Security, L. Batten, D. S. Kim, X. Zhang, and G. Li, Eds. Singapore: Springer, 2017, pp. 100-110.
  37. M. Xue, C. Yuan, H. Wu, Y. Zhang, and W. Liu, ''Machine learning secu- rity: Threats, countermeasures, and evaluations,'' IEEE Access, vol. 8, pp. 74720-74742, 2020.
  38. S. Chang and C. Li, ''Privacy in neural network learning: Threats and countermeasures,'' IEEE Netw., vol. 32, no. 4, pp. 61-67, Aug. 2018.
  39. D. Zhang, X. Chen, D. Wang, and J. Shi, ''A survey on collaborative deep learning and privacy-preserving,'' in Proc. IEEE 3rd Int. Conf. Data Sci. Cyberspace (DSC), Jun. 2018, pp. 652-658.
  40. C. Dwork and A. Roth, ''The algorithmic foundations of differential pri- vacy,'' Found. Trends Theor. Comput. Sci., vol. 9, nos. 3-4, pp. 211-407, Aug. 2014, doi: 10.1561/0400000042. · DOI · Paper page
  41. C. Dwork, K. Kenthapadi, F. McSherry, I. Mironov, and M. Naor, ''Our data, ourselves: Privacy via distributed noise generation,'' in Proc. 24th Annu. Int. Conf. The Theory Appl. Cryptograph. Techn., Berlin, Germany: Springer, 2006, pp. 486-503.
  42. C. Dwork, F. McSherry, K. Nissim, and A. Smith, ''Calibrating noise to sensitivity in private data analysis,'' in Theory Cryptography, S. Halevi and T. Rabin, Eds. Berlin, Germany: Springer, 2006, pp. 265-284.
  43. I. Mironov, ''Rényi differential privacy,'' in Proc. IEEE 30th Comput. Secur. Found. Symp. (CSF), Aug. 2017, pp. 263-275.
  44. J. Dong, A. Roth, and W. J. Su, ''Gaussian differential privacy,'' CoRR, New York, NY, USA, Tech. Rep. 1905.02383, 2019.
  45. A. Ghosh, T. Roughgarden, and M. Sundararajan, ''Universally utility- maximizing privacy mechanisms,'' SIAM J. Comput., vol. 41, no. 6, pp. 1673-1693, 2012, doi: 10.1137/09076828X. · DOI
  46. F. Fioretto, P. Van Hentenryck, and K. Zhu, ''Differential privacy of hier- archical census data: An optimization approach,'' Artif. Intell., vol. 296, Jul. 2021, Art. no. 103475.
  47. V. Balcer and S. Vadhan, ''Differential privacy on finite computers,'' CoRR, New York, NY, USA, Tech. Rep. 1709.05396, 2019.
  48. F. McSherry and K. Talwar, ''Mechanism design via differential privacy,'' in Proc. 48th Annu. IEEE Symp. Found. Comput. Sci. (FOCS), Oct. 2007, pp. 94-103.
  49. N. Agarwal, A. T. Suresh, F. Yu, S. Kumar, and H. B. McMahan, ''CPSGD: Communication-efficient and differentially-private distributed SGD,'' Curran Associates, Red Hook, NY, USA, Tech. Rep. NIPS'18, 2018.
  50. C. Dwork, G. N. Rothblum, and S. Vadhan, ''Boosting and differential privacy,'' in Proc. IEEE 51st Annu. Symp. Found. Comput. Sci., Oct. 2010, pp. 51-60.
  51. A. Rényi, ''On measures of entropy and information,'' in Proc. 4th Berkeley Symp. Math. Statist. Probab., 1961, pp. 547-561.
  52. M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, ''Deep learning with differential privacy,'' in Proc. ACM SIGSAC Conf. Comput. Commun. Secur., Oct. 2016, pp. 308-318, doi: 10.1145/2976749.2978318. · DOI · Paper page
  53. S. Asoodeh, J. Liao, F. P. Calmon, O. Kosut, and L. Sankar, ''Three variants of differential privacy: Lossless conversion and applications,'' IEEE J. Sel. Areas Inf. Theory, vol. 2, no. 1, pp. 208-222, Mar. 2021.
  54. K. Pan, M. Gong, K. Feng, and K. Wang, ''Differentially private regres- sion analysis with dynamic privacy allocation,'' Knowl.-Based Syst., vol. 217, Apr. 2021, Art. no. 106795.
  55. J. Zhang, Z. Zhang, X. Xiao, Y. Yang, and M. Winslett, ''Func- tional mechanism: Regression analysis under differential privacy,'' Proc. VLDB Endowment, vol. 5, no. 11, pp. 1364-1375, 2012, doi: 10.14778/ 2350229.2350253. · DOI
  56. M. Gong, K. Pan, and Y. Xie, ''Differential privacy preservation in regression analysis based on relevance,'' Knowl.-Based Syst., vol. 173, pp. 140-149, Jun. 2019.
  57. X. Fang, F. Yu, G. Yang, and Y. Qu, ''Regression analysis with differential privacy preserving,'' IEEE Access, vol. 7, pp. 129353-129361, 2019.
  58. K. Ligett, S. Neel, A. Roth, B. Waggoner, and Z. S. Wu, ''Accuracy first: Selecting a differential privacy level for accuracy-constrained ERM,'' CoRR, New York, NY, USA, Tech. Rep. 1705.10829, 2017.
  59. J. Lee and C. W. Clifton, ''Top-k frequent itemsets via differentially pri- vate FP-trees,'' in Proc. 20th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Aug. 2014, pp. 931-940, doi: 10.1145/2623330.2623723. · DOI
  60. Z. Sun, Y. Wang, M. Shu, R. Liu, and H. Zhao, ''Differential privacy for data and model publishing of medical data,'' IEEE Access, vol. 7, pp. 152103-152114, 2019.
  61. P. Tang, X. Cheng, S. Su, R. Chen, and H. Shao, ''Differentially private publication of vertically partitioned data,'' IEEE Trans. Depend. Secure Comput., vol. 18, no. 2, pp. 780-795, Mar. 2021.
  62. R. Chen, G. Acs, and C. Castelluccia, ''Differentially private sequen- tial data publication via variable-length n-grams,'' in Proc. ACM Conf. Comput. Commun. Secur. (CCS), 2012, pp. 638-649, doi: 10.1145/ 2382196.2382263. · DOI
  63. M. Hay, V. Rastogi, G. Miklau, and D. Suciu, ''Boosting the accu- racy of differentially private histograms through consistency,'' Proc. VLDB Endowment, vol. 3, nos. 1-2, pp. 1021-1032, Sep. 2010, doi: 10.14778/1920841.1920970. · DOI
  64. Y. Xiao, L. Xiong, and C. Yuan, ''Differentially private data release through multidimensional partitioning,'' in Secure Data Management, W. Jonker and M. Petković, Eds. Berlin, Germany: Springer, 2010, pp. 150-168.
  65. C. Li, M. Hay, V. Rastogi, G. Miklau, and A. McGregor, ''Optimizing linear counting queries under differential privacy,'' in Proc. 29th ACM SIGMOD-SIGACT-SIGART Symp. Princ. Database Syst. Data (PODS), 2010, pp. 123-134, doi: 10.1145/1807085.1807104. · DOI
  66. D. Huang, S. Han, X. Li, and P. S. Yu, ''Orthogonal mechanism for answering batch queries with differential privacy,'' in Proc. 27th Int. Conf. Sci. Stat. Database Manage., Jun. 2015, pp. 1-10, doi: 10.1145/ 2791347.2791378. · DOI
  67. L. Fan and L. Xiong, ''An adaptive approach to real-time aggregate monitoring with differential privacy,'' IEEE Trans. Knowl. Data Eng., vol. 26, no. 9, pp. 2094-2106, Sep. 2014.
  68. H. Huang, D. Zhang, F. Xiao, K. Wang, J. Gu, and R. Wang, ''Privacy- preserving approach PBCN in social network with differential pri- vacy,'' IEEE Trans. Netw. Service Manage., vol. 17, no. 2, pp. 931-945, Jun. 2020.
  69. M. Fredrikson, S. Jha, and T. Ristenpart, ''Model inversion attacks that exploit confidence information and basic countermeasures,'' in Proc. 22nd ACM SIGSAC Conf. Comput. Commun. Secur., Oct. 2015, pp. 1322-1333, doi: 10.1145/2810103.2813677. · DOI · Paper page
  70. M. Fredrikson, E. Lantz, S. Jha, S. Lin, D. Page, and T. Ristenpart, ''Privacy in pharmacogenetics: An end-to-end case study of personalized warfarin dosing,'' in Proc. 23rd USENIX Conf. Secur. Symp. (SEC), Berkeley, CA, USA: USENIX Association, 2014, pp. 17-32.
  71. K. Ligett, S. Neel, A. Roth, B. Waggoner, and S. Z. Wu, ''Accuracy first: Selecting a differential privacy level for accuracy constrained ERM,'' in Proc. Adv. Neural Inf. Process. Syst., vol. 30, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds. Red Hook, NY, USA: Curran Associates, 2017, pp. 2563-2573.
  72. R. Hu, Y. Guo, E. P. Ratazzi, and Y. Gong, ''Differentially private federated learning for resource-constrained Internet of Things,'' CoRR, New York, NY, USA, Tech. Rep. 2003.12705, 2020.
  73. M. Xu and X. Li, ''Subject property inference attack in collaborative learning,'' in Proc. 12th Int. Conf. Intell. Hum.-Mach. Syst. Cybern. (IHMSC), Aug. 2020, pp. 227-231.
  74. Y. Qiao, Z. Liu, H. Lv, M. Li, Z. Huang, Z. Li, and W. Liu, ''An effective data privacy protection algorithm based on differential privacy in edge computing,'' IEEE Access, vol. 7, pp. 136203-136213, 2019.
  75. G. Cormode, C. Procopiuc, D. Srivastava, E. Shen, and T. Yu, ''Differen- tially private spatial decompositions,'' in Proc. IEEE 28th Int. Conf. Data Eng., Apr. 2012, pp. 20-31.
  76. C. Li, M. Hay, G. Miklau, and Y. Wang, ''A data-and workload-aware algorithm for range queries under differential privacy,'' Proc. VLDB Endowment, 2014.
  77. W. Qardaji, W. Yang, and N. Li, ''Understanding hierarchical methods for differentially private histograms,'' Proc. VLDB Endowment, vol. 6, no. 14, pp. 1954-1965, Sep. 2013.
  78. R. Bassily, ''Linear queries estimation with local differential privacy,'' CoRR, New York, NY, USA, Tech. Rep. 1810.02810, 2018.
  79. Y. Abakarim, M. Lahby, and A. Attioui, ''Towards an efficient real-time approach to loan credit approval using deep learning,'' in Proc. 9th Int. Symp. Signal, Image, Video Commun. (ISIVC), Nov. 2018, pp. 306-313.
  80. W. Wang, J. Lee, F. Harrou, and Y. Sun, ''Early detection of Parkinson's disease using deep learning and machine learning,'' IEEE Access, vol. 8, pp. 147635-147646, 2020.
  81. W. K. Al-Jibory and A. El-Zaart, ''Edge detection for diagnosis early Alzheimer's disease by using Weibull distribution,'' in Proc. 25th Int. Conf. Microelectron. (ICM), Dec. 2013, pp. 1-5.
  82. T. Wang, N. Li, and S. Jha, ''Locally differentially private frequent itemset mining,'' in Proc. IEEE Symp. Secur. Privacy, (SP), San Francisco, CA, USA, May 2018, pp. 127-143, doi: 10.1109/SP.2018.00035. · DOI
  83. M. Maruseac and G. Ghinita, ''Precision-enhanced differentially-private mining of high-confidence association rules,'' IEEE Trans. Depend. Secure Comput., vol. 17, no. 6, pp. 1297-1309, Nov. 2020.
  84. D. Su, J. Cao, N. Li, and M. Lyu, ''PrivPfC: Differentially pri- vate data publication for classification,'' VLDB J. Int. Very Large Data Bases, vol. 27, no. 2, pp. 201-223, Apr. 2018, doi: 10.1007/ s00778-017-0492-3. · DOI
  85. Y. Zhang, Z. Hao, and S. Wang, ''A differential privacy support vector machine classifier based on dual variable perturbation,'' IEEE Access, vol. 7, pp. 98238-98251, 2019.
  86. N. L. Zhang, ''Hierarchical latent class models for cluster analysis,'' J. Mach. Learn. Res., vol. 5, pp. 697-723, Dec. 2004.
  87. N. Mohammed, D. Alhadidi, B. C. M. Fung, and M. Debbabi, ''Secure two-party differentially private data release for vertically partitioned data,'' IEEE Trans. Depend. Secure Comput., vol. 11, no. 1, pp. 59-71, Jan. 2014.
  88. R. J. Lewis, ''An introduction to classification and regression tree (CART) analysis,'' in Proc. Annu. Meeting Soc. Academic Emergency Med., 2000, pp. 1-14.
  89. R. Agrawal and R. Srikant, ''Fast algorithms for mining association rules in large databases,'' in Proc. 20th Int. Conf. Very Large Data Bases (VLDB). San Francisco, CA, USA: Morgan Kaufmann Publishers, 1994, pp. 487-499.
  90. J. Han, J. Pei, and Y. Yin, ''Mining frequent patterns without candidate generation,'' ACM SIGMOD Rec., vol. 29, no. 2, pp. 1-12, 2000, doi: 10.1145/335191.335372. · DOI · Paper page
  91. R. Chen, B. C. M. Fung, and B. C. Desai, ''Differentially private trajectory data publication,'' CoRR, New York, NY, USA, Tech. Rep. 1112.2020, 2011.
  92. F. McSherry and R. Mahajan, ''Differentially-private network trace analysis,'' ACM SIGCOMM Comput. Commun. Rev., vol. 40, no. 4, pp. 123-134, Aug. 2010, doi: 10.1145/1851275.1851199. · DOI
  93. R. Chen, B. C. M. Fung, P. S. Yu, and B. C. Desai, ''Correlated net- work data publication via differential privacy,'' VLDB J., vol. 23, no. 4, pp. 653-676, Aug. 2014, doi: 10.1007/s00778-013-0344-8. · DOI
  94. X. Ying and X. Wu, ''Randomizing social networks: A spectrum preserv- ing approach,'' in Proc. SIAM Int. Conf. Data Mining, 2008, pp. 739-750, doi: 10.1137/1.9781611972788.67. · DOI
  95. B. Bebensee, ''Local differential privacy: A tutorial,'' CoRR, New York, NY, USA, Tech. Rep. 1907.11908, 2019.
  96. H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas, ''Communication-efficient learning of deep networks from decentral- ized data,'' in Artificial Intelligence and Statistics, vol. 54. Fort Lauderdale, FL, USA, Apr. 2017, pp. 1273-1282. [Online]. Available: http://proceedings.mlr.press/v54/mcmahan17a.html
  97. Z. Yu, J. Hu, G. Min, Z. Wang, W. Miao, and S. Li, ''Privacy-preserving federated deep learning for cooperative hierarchical caching in fog com- puting,'' IEEE Internet Things J., early access, May 18, 2021, doi: 10.1109/JIOT.2021.3081480. · DOI
  98. L. Yin, J. Feng, H. Xun, Z. Sun, and X. Cheng, ''A privacy-preserving federated learning for multiparty data sharing in social IoTs,'' IEEE Trans. Netw. Sci. Eng., vol. 8, no. 3, pp. 2706-2718, Jul. 2021.
  99. K. Wei, J. Li, M. Ding, C. Ma, H. Su, B. Zhang, and H. V. Poor, ''User- level privacy-preserving federated learning: Analysis and performance optimization,'' IEEE Trans. Mobile Comput., early access, Feb. 4, 2021, doi: 10.1109/TMC.2021.3056991. · DOI
  100. Y. Liu, R. Zhao, J. Kang, A. Yassine, D. Niyato, and J. Peng, ''Towards communication-efficient and attack-resistant federated edge learning for industrial Internet of Things,'' ACM Trans. Internet Technol., New York, NY, USA, Tech. Rep. 1533-5399, 2020.
  101. A. Sonee and S. Rini, ''Efficient federated learning over multiple access channel with differential privacy constraints,'' CoRR, New York, NY, USA, Tech. Rep. 2005.07776, 2020.
  102. H. Wu, C. Chen, and L. Wang, ''A theoretical perspective on differentially private federated multi-task learning,'' 2020, arXiv:2011.07179. · arXiv
  103. P. C. M. Arachchige, P. Bertok, I. Khalil, D. Liu, S. Camtepe, and M. Atiquzzaman, ''Local differential privacy for deep learning,'' IEEE Internet Things J., vol. 7, no. 7, pp. 5827-5842, Jul. 2020.
  104. M. Gong, J. Feng, and Y. Xie, ''Privacy-enhanced multi-party deep learning,'' Neural Netw., vol. 121, pp. 484-496, Jan. 2020.
  105. A.-T. Tran, T.-D. Luong, J. Karnjana, and V.-N. Huynh, ''An efficient approach for privacy preserving decentralized deep learning models based on secure multi-party computation,'' Neurocomputing, vol. 422, pp. 245-262, Jan. 2021.
  106. Y. Li, Y. Zhou, A. Jolfaei, D. Yu, G. Xu, and X. Zheng, ''Privacy- preserving federated learning framework based on chained secure multi- party computing,'' IEEE Internet Things J., vol. 8, no. 8, pp. 6178-6186, Apr. 2021.
  107. X. Wu, M. Fredrikson, S. Jha, and J. F. Naughton, ''A methodology for formalizing model-inversion attacks,'' in Proc. IEEE 29th Comput. Secur. Found. Symp. (CSF), Jun. 2016, pp. 355-370.
  108. Z. Yang, J. Zhang, E.-C. Chang, and Z. Liang, ''Neural network inversion in adversarial setting via background knowledge alignment,'' in Proc. ACM SIGSAC Conf. Comput. Commun. Secur., Nov. 2019, pp. 225-240, doi: 10.1145/3319535.3354261. · DOI
  109. C. Fung, C. J. M. Yoon, and I. Beschastnikh, ''The limitations of fed- erated learning in Sybil settings,'' in Proc. 23rd Int. Symp. Res. Attacks, Intrusions Defenses (RAID). San Sebastian, Spain: USENIX Association, Oct. 2020, pp. 301-316. [Online]. Available: https://www.usenix.org/ conference/raid2020/presentation/fung
  110. M. Fang, X. Cao, J. Jia, and N. Gong, ''Local model poisoning attacks to Byzantine-robust federated learning,'' in Proc. USENIX Secur., Aug. 2020, pp. 1605-1622.
  111. Y. Zhang and Q. Yang, ''A survey on multi-task learning,'' CoRR, New York, NY, USA, Tech. Rep. 1707.08114, 2018.
  112. M. Crawshaw, ''Multi-task learning with deep neural networks: A sur- vey,'' CoRR, New York, NY, USA, Tech. Rep. 2009.09796, 2020.
  113. R. Xu, N. Baracaldo, Y. Zhou, A. Anwar, and H. Ludwig, ''HybridAlpha: An efficient approach for privacy-preserving federated learning,'' in Proc. 12th ACM Workshop Artif. Intell. Secur. (AISec), 2019, pp. 13-23, doi: 10.1145/3338501.3357371. · DOI
  114. A. Triastcyn and B. Faltings, ''Federated learning with Bayesian differ- ential privacy,'' in Proc. IEEE Int. Conf. Big Data (Big Data), Dec. 2019, pp. 2587-2596.
  115. T. Wang, J. Blocki, N. Li, and S. Jha, ''Locally differentially private protocols for frequency estimation,'' in Proc. 26th USENIX Conf. Secur. Symp., Berkeley, CA, USA: USENIX Association, 2017, pp. 729-745.
  116. F. Farokhi, N. Wu, D. Smith, and M. A. Kaafar, ''The cost of privacy in asynchronous differentially-private machine learning,'' IEEE Trans. Inf. Forensics Security, vol. 16, pp. 2118-2129, 2021.
  117. P. Kairouz, S. Oh, and P. Viswanath, ''Extremal mechanisms for local dif- ferential privacy,'' J. Mach. Learn. Res., vol. 17, pp. 492-542, Jan. 2016.
  118. G. Cormode, Count-Min Sketch. Boston, MA, USA: Springer, 2009, pp. 511-516.
  119. R. Bassily and A. Smith, ''Local, private, efficient protocols for succinct histograms,'' in Proc. 47th Annu. ACM Symp. Theory Comput., Jun. 2015, pp. 127-135, doi: 10.1145/2746539.2746632. · DOI
  120. J. C. Duchi, M. I. Jordan, and M. J. Wainwright, ''Local privacy and sta- tistical minimax rates,'' in Proc. IEEE 54th Annu. Symp. Found. Comput. Sci., Oct. 2013, pp. 429-438.
  121. J. C. Duchi, M. Jordan, and M. J. Wainwright, ''Local privacy and minimax bounds: Sharp rates for probability estimation,'' in Proc. 26th Int. Conf. Neural Inf. Process. Syst., vol. 1. Red Hook, NY, USA: Curran Associates Inc., 2013, pp. 1529-1537.
  122. J. Duchi, M. Wainwright, and M. Jordan, ''Minimax optimal proce- dures for locally private estimation,'' arXiv, New York, NY, USA, Tech. Rep. 1604.02390, 2017.
  123. B. H. Bloom, ''Space/time trade-offs in hash coding with allowable errors,'' Commun. ACM, vol. 13, no. 7, pp. 422-426, Jul. 1970, doi: 10.1145/362686.362692. · DOI
  124. G. Bianchi, L. Bracciale, and P. Loreti, '''Better than nothing' privacy with Bloom filters: To what extent?'' in Privacy in Statistical Databases, J. Domingo-Ferrer and I. Tinnirello, Eds. Berlin, Germany: Springer, 2012, pp. 348-363.
  125. C. Dwork, K. Kenthapadi, F. McSherry, I. Mironov, and M. Naor, ''Our data, ourselves: Privacy via distributed noise generation,'' in Advances in Cryptology EUROCRYPT 2006, S. Vaudenay, Ed. Berlin, Germany: Springer, 2006, pp. 486-503.
  126. C. Dwork and J. Lei, ''Differential privacy and robust statistics,'' in Proc. 41st Annu. ACM Symp. Symp. theory Comput. (STOC), 2009, pp. 371-380, doi: 10.1145/1536414.1536466. · DOI
  127. S. Asoodeh, J. Liao, F. P. Calmon, O. Kosut, and L. Sankar, ''Three variants of differential privacy: Lossless conversion and applications,'' IEEE J. Sel. Areas Inf. Theory, 2021.

Cited by

Sorted by citations

Authors
Ouadrhiri, A. E., & Abdelhadi, A.
Affiliations
University of Houston (US)
ORCID
Venue
IEEE Access
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2022
Volume
10
Pages
22359-22380
ISSN
2169-3536 (ISSN-L)
DOI
10.1109/access.2022.3151670
OpenAlex
W4213044365
Cited by
445
References
9
Citations by year
2026: 105 · 2025: 162 · 2024: 113 · 2023: 54 · 2022: 11
FWCI
27.97
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
  • Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
Keywords
differential privacy, federated learning, deep learning privacy, privacy-preserving machine learning, noise addition, privacy-utility trade-off, model privacy

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