Page 504 - 《软件学报》2025年第7期
P. 504

张朋飞 等: 基于自适应剪枝的满足本地差分隐私的真值发现算法                                                  3425



                                               表 3 Syn: 不同数据分布的鲁棒性

                                   分布                  对比算法                    MAE Change
                                                        VarFil                   0.647 1
                                                        TLayer                   0.832 2
                                                        PairsTD                  0.763 6
                                   Ran
                                                       PrivTDSI                  0.632 1
                                                        TESLA                    0.455 5
                                                       NATURE                    0.243 4
                                                        VarFil                   0.644 6
                                                        TLayer                   0.830 8
                                                        PairsTD                  0.761 2
                                   Lap
                                                       PrivTDSI                  0.628 9
                                                        TESLA                    0.453 1
                                                       NATURE                    0.242 0
                                                        VarFil                   0.645 8
                                                        TLayer                   0.831 3
                                                        PairsTD                  0.762 5
                                   Gau
                                                       PrivTDSI                  0.630 3
                                                        TESLA                    0.454 2
                                                       NATURE                    0.242 4

                 6   结束语

                    本文针对连续值场景, 基于本地差分隐私研究了目前已有研究工作中尚未充分考虑的含异常值的真值发现问
                 题, 并针对此问题提出       NATURE  算法, 然后从理论上分析了算法的隐私、效用和复杂度, 最后在两个真实数据集
                 和一个合成数据集上验证了算法的有效性. 在有些场景下, 工人提交数据可能是离散值, 甚至是文本、图像等, 在
                 未来研究中, 拟针对上述场景下高效率且高效用的本地差分隐私的真值发现问题做进一步探索.

                 References:
                  [1]  Xiong JB, Bi RW, Tian YL, Liu XM, Ma JF. Security and privacy in mobile crowdsensing: Models, progresses, and trends. Chinese
                     Journal of Computers, 2021, 44(9): 1949–1966 (in Chinese with English abstract). [doi: 10.11897/SP.J.1016.2021.01949]
                  [2]  Tong YX, Yuan Y, Cheng YR, Chen L, Wang GR. Survey on spatiotemporal crowdsourced data management techniques. Ruan Jian Xue
                     Bao/Journal  of  Software,  2017,  28(1):  35–58  (in  Chinese  with  English  abstract).  http://www.jos.org.cn/1000-9825/5140.htm  [doi:  10.
                     13328/j.cnki.jos.005140]
                  [3]  Chai CL, Li GL, Zhao TY, Luo YY, Yu MH. Crowd-powered database system: A survey. Chinese Journal of Computers, 2020, 43(5):
                     948–972 (in Chinese with English abstract). [doi: 10.11897/SP.J.1016.2020.00948]
                  [4]  Feng JH, Li GL, Feng JH. A survey on crowdsourcing. Chinese Journal of Computers, 2015, 38(9): 1713–1726 (in Chinese with English
                     abstract). [doi: 10.11897/SP.J.1016.2015.01713]
                  [5]  Ji SL, Du TY, Li JF, Shen C, Li B. Security and privacy of machine learning models: A survey. Ruan Jian Xue Bao/Journal of Software,
                     2021, 32(1): 41–67 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6131.htm [doi: 10.13328/j.cnki.jos.006131]
                  [6]  Li Q, Li YL, Gao J, Su L, Zhao B, Demirbas M, Fan W, Han JW. A confidence-aware approach for truth discovery on long-tail data.
                     Proc. of the VLDB Endowment, 2014, 8(4): 425–436. [doi: 10.14778/2735496.2735505]
                  [7]  Li  Q,  Li  YL,  Gao  J,  Zhao  B,  Fan  W,  Han  JW.  Resolving  conflicts  in  heterogeneous  data  by  truth  discovery  and  source  reliability
                     estimation. In: Proc. of the 2014 ACM SIGMOD Int’l Conf. on Management of Data. Snowbird: ACM, 2014. 1187–1198. [doi: 10.1145/
                     2588555.2610509]
                  [8]  Zeng JR, Chen H, Peng H, Wu Y, Li CP, Wang S. Privacy preservation in mobile participatory sensing. Chinese Journal of Computers,
                     2016, 39(3): 595–614 (in Chinese with English abstract). [doi: 10.11897/SP.J.1016.2016.00595]
                  [9]  Zheng  YF,  Duan  HY,  Yuan  XL,  Wang  C.  Privacy-aware  and  efficient  mobile  crowdsensing  with  truth  discovery.  IEEE  Trans.  on
                     Dependable and Secure Computing, 2020, 17(1): 121–133. [doi: 10.1109/TDSC.2017.2753245]
                 [10]  Ye QQ, Meng XF, Zhu MJ, Huo Z. Survey on local differential privacy. Ruan Jian Xue Bao/Journal of Software, 2018, 29(7): 1981–2005
   499   500   501   502   503   504   505   506   507   508