Abstract
Data aggregation based on machine learning (ML), in mobile edge computing, allows participants to send ephemeral parameter updates of local ML on their private data instead of the exact data to the untrusted aggregator. However, it still enables the untrusted aggregator to reconstruct participants’ private data, although parameter updates contain significantly less information than the private data. Existing work either incurs extremely high overhead or ignores malicious participants dropping out. The latest research deals with the dropouts with desirable cost, but it is vulnerable to malformed message attacks. To this end, we focus on the data aggregation based on ML in a practical setting where malicious participants may send malformed parameter updates to perturb the total parameter updates learned by the aggregator. Moreover, malicious participants may drop out and collude with other participants or the untrusted aggregator. In such a scenario, we propose a scheme named DAML, which to the best of our knowledge is the first attempt toward verifying participants’ submissions in data aggregation based on ML. The main idea is to validate participants’ submissions via SSVP, a novel secret-shared verification protocol, and then aggregate participants’ parameter updates using SDA, a secure data aggregation protocol. Simulation results demonstrate that DAML can protect participants’ data privacy with preferable overhead.
- M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang. 2016. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS’16).Google Scholar
- Asmaa Abdallah and Xuemin Sherman Shen. 2018. A lightweight lattice-based homomorphic privacy-preserving data aggregation scheme for smart grid. IEEE Transactions on Smart Grid 9, 1 (2018), 396--405.Google ScholarCross Ref
- Gergely Ács and Claude Castelluccia. 2011. I have a dream! (differentially private smart metering). In Proceedings of International Workshop on Information Hiding.Google ScholarCross Ref
- Wael Alghamdi, Mohsen Rezvani, Hui Wu, and Salil S. Kanhere. 2019. Routing-aware and malicious node detection in a concealed data aggregation for WSNs. ACM Transactions on Sensor Networks 15, 2 (2019), 1--18.Google ScholarDigital Library
- Toshinori Araki, Jun Furukawa, Yehuda Lindell, Ariel Nof, and Kazuma Ohara. 2016. High-throughput semi-honest secure three-party computation with an honest majority. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS’16).Google ScholarDigital Library
- Saman Atapattu, Nathan Ross, Yindi Jing, Yuanyuan He, and Jamie S. Evans. 2019. Physical-layer security in full-duplex multi-hop multi-user wireless network with relay selection. IEEE Transactions on Wireless Communications 18, 2 (2019), 1216--1232.Google ScholarDigital Library
- E. Ben-Sasson, A. Chiesa, and D. Genkin. 2013. SNARKs for C: Verifying program executions succinctly and in zero knowledge. In Advances in Cryptology—CRYPTO 2013. Lecture Notes in Computer Science, Vol. 8043. Springer, 90--108.Google Scholar
- E. Ben-Sasson, S. Fehr, and R. Ostrovsky. 2012. Near-linear unconditionally-secure multiparty computation with a dishonest minority. In Advances in Cryptology—CRYPTO 2012. Lecture Notes in Computer Science, Vol. 7417. Springer, 663--680.Google Scholar
- Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2017. Practical secure aggregation for privacy-preserving machine learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS’17).Google ScholarDigital Library
- T.-H. Hubert Chan, Elaine Shi, and Dawn Song. 2012. Privacy-preserving stream aggregation with fault tolerance. In Proceedings of International Conference on Financial Cryptography and Data Security.Google ScholarCross Ref
- Yuwen Chen, José-Fernán Martínez, Pedro Castillejo, and Lourdes López. 2019. A homomorphic based multiple data aggregation scheme for smart grid. IEEE Sensors Journal 19, 10 (2019), 3921--3929.Google ScholarCross Ref
- Henry Corrigan-Gibbs and Dan Boneh. 2017. Prio: Private, robust, and scalable computation of aggregate statistics. In Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI’17).Google Scholar
- Henry Corrigan-Gibbs, David Isaac Wolinsky, and Bryan Ford. 2013. Proactively accountable anonymous messaging in Verdict. In Proceedings of the 2013 USENIX Security Symposium.Google Scholar
- Hongwei Duan, Runmeng Du, Qiong Wei, Wenli Wang, and Xin Liu. 2018. Efficient collusion-tolerable secure multiparty computation of weighted average. In Proceedings of the IEEE International Conference on Computational Intelligence and Security (CIS’18).Google ScholarCross Ref
- C. Dwork and J. Lei. 2009. Differential privacy and robust statistics. In Proceedings of the ACM Symposium on Theory of Computing.Google Scholar
- Tariq Elahi, George Danezis, and Ian Goldberg. 2014. Privex: Private collection of traffic statistics for anonymous communication networks. In Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security (CCS’14).Google ScholarDigital Library
- G. Fanti, V. Pihur, and U. Erlingsson. 2016. Building a RAPPOR with the unknown: Privacy-preserving learning of associations and data dictionaries. Proceedings on Privacy Enhancing Technologies 3, 1 (2016), 41--61.Google ScholarCross Ref
- R. Gennaro, C. Gentry, and B. Parno. 2013. Quadratic span programs and succinct NIZKs without PCPs. In Proceedings of the International Conference on the Theory and Applications of Cryptographic Techniques.Google Scholar
- Shafi Goldwasser, Silvio Micali, and Charles Rackoff. 1989. The knowledge complexity of interactive proof systems. SIAM Journal on Computing 18, 1 (1989), 186--208.Google ScholarDigital Library
- Philippe Golle and Ari Juels. 2004. Dining cryptographers revisited. In Proceedings of the International Conference on the Theory and Applications of Cryptographic Techniques.Google ScholarCross Ref
- Slawomir Goryczka and Li Xiong. 2017. A comprehensive comparison of multiparty secure additions with differential privacy. IEEE Transactions on Dependable and Secure Computing 14, 5 (2017), 463--477.Google ScholarCross Ref
- A. Greenberg. 2016. Apple’s ‘Differential Privacy’ Is About Collecting Your Data—But Not Your Data.Retrieved July 7, 2020 from https://www.wired.com/2016/06/apples-differential-privacy-collecting-data/.Google Scholar
- Shai Halevi, Yehuda Lindell, and Benny Pinkas. 2011. Secure computation on the web: Computing without simultaneous interaction. In Proceedings of the Annual Cryptology Conference.Google ScholarCross Ref
- Bret Hull, Vladimir Bychkovsky, Yang Zhang, Kevin Chen, Michel Goraczko, Allen Miu, Eugene Shih, Hari Balakrishnan, and Samuel Madden. 2006. CarTel: A distributed mobile sensor computing system. In Proceedings of the International Conference on Embedded Networked Sensor Systems.Google ScholarDigital Library
- T. Hunt, C. Song, R. Shokri, V. Shmatikov, and E Witchel. 2018. Chiron: Privacy-preserving machine learning as a service. arXiv:1803.05961.Google Scholar
- Rob Jansen and Aaron Johnson. 2016. Safely measuring Tor. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS’16). 1553--1567.Google ScholarDigital Library
- Taeho Jung, Xiang-Yang Li, and Meng Wan. 2015. Collusion-tolerable privacy-preserving sum and product calculation without secure channel. IEEE Transactions on Dependable and Secure Computing 12, 1 (2015), 45--57.Google ScholarCross Ref
- T. Jung, Z. Li, X.-Y. Wan, and M. Wan. 2013. Privacy preserving cloud data access with multi-authorities. In Proceedings of the 2013 IEEE INFOCOM Conference.Google Scholar
- Y. LeCun, Y. Bengio, and G. Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444.Google Scholar
- Q. Li, G. Cao, and T. F. L. Porta. 2014. Efficient and privacy-aware data aggregation in mobile sensing. IEEE Transactions on Dependable and Secure Computing 11, 2 (2014), 115--129.Google ScholarDigital Library
- Shaohua Li, Kaiping Xue, Qingyou Yang, and Peilin Hong. 2018c. PPMA: Privacy-preserving multisubset data aggregation in smart grid. IEEE Transactions on Industrial Informatics 14, 2 (2018), 462--471.Google ScholarCross Ref
- Xiong Li, Shanpeng Liu, Fan Wu, and Saru Kumari. 2018a. Privacy preserving data aggregation scheme for mobile edge computing assisted IoT applications. IEEE Internet of Things Journal 6, 3 (2018), 4755--4763.Google ScholarCross Ref
- Xujing Li, Wei Liu, Mande Xie, Anfeng Liu, and Ming Zhao. 2018b. Differentiated data aggregation routing scheme for energy conserving and delay sensitive wireless sensor networks. Sensors 18, 7 (2018), 2349--2378.Google ScholarCross Ref
- Xuening Liao, Yuanyu Zhang, Zhenqiang Wu, Yulong Shen, Xiaohong Jiang, and Hiroshi Inamura. 2018. On security-delay trade-off in two-hop wireless networks with buffer-aided relay selection. IEEE Transactions on Wireless Communications 17, 3 (2018), 1893--1906.Google ScholarCross Ref
- Yehuda Lindell, Benny Pinkas, Nigel P. Smart, and Avishay Yanai. 2015. Efficient constant round multi-party computation combining BMR and SPDZ. In Proceedings of the Annual Cryptology Conference.Google ScholarCross Ref
- Yining Liu, Wei Guo, Chun-I. Fan, Liang Chang, and Chi Cheng. 2018. A practical privacy-preserving data aggregation (3PDA) scheme for smart grid. IEEE Transactions on Industrial Informatics 15, 3 (2018), 1767--1774.Google ScholarCross Ref
- Yi-Ning Liu, Yan-Ping Wang, Xiao-Fen Wang, Zhe Xia, and Jing-Fang Xu. 2019. Privacy-preserving raw data collection without a trusted authority for IoT. Computer Networks 148 (2019), 340--348.Google ScholarCross Ref
- P. Mohassel and Y. Zhang. 2017. SecureML: A system for scalable privacy-preserving machine learning. In Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP’17).Google Scholar
- Jiangtian Nie, Jun Luo, Zehui Xiong, Dusit Niyato, and Wang Ping. 2019. A Stackelberg game approach towards socially-aware incentive mechanisms for mobile crowdsensing. IEEE Transactions on Wireless Communications 18, 1 (2019), 724--738.Google ScholarDigital Library
- X. Pan, J. Chen, R. Monga, S. Bengio, and R. Jozefowicz. 2017. Revisiting distributed synchronous SGD. arXiv:1702.05800.Google Scholar
- A. Shamir. 1979. How to share a secret. Communications of the ACM 22, 11 (1979), 612--613.Google ScholarDigital Library
- Rashid Sheikh and Durgesh Kumar Mishra. 2019. Secure sum computation using homomorphic encryption. In Data Science and Big Data Analytics. Springer, 357--363.Google Scholar
- Runting Shi, Richard Chow, and Tsz Hong Hubert Chan. 2013. Privacy-preserving aggregation of time-series data. US Patent 8,555,400.Google Scholar
- R. Shokri, M. Stronati, C. Song, and V. Shmatikov. 2017. Membership inference attacks against machine learning models. In Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP’17).Google Scholar
- Arvind Thiagarajan, Lenin Ravindranath, Katrina Lacurts, Samuel Madden, Hari Balakrishnan, Sivan Toledo, and Jakob Eriksson. 2009. VTrack: Accurate, energy-aware road traffic delay estimation using mobile phones. In Proceedings of the ACM Conference on Embedded Networked Sensor Systems.Google ScholarDigital Library
- Marcel von Maltitz, Dominik Bitzer, and Georg Carle. 2019. Data querying and access control for secure multiparty computation. arXiv:1901.02651.Google Scholar
- Q. Wang, Y. Zhang, X. Lu, Z. Wang, Z. Qin, and K. Ren. 2018. Real-time and spatio-temporal crowd-sourced social network data publishing with differential privacy. IEEE Transactions on Dependable and Secure Computing 15, 4 (2018), 591--606.Google ScholarDigital Library
- Z. Wang, J. Hu, R. Lv, J. Wei, Q. Wang, D. Yang, and H. Qi. 2019. Personalized privacy-preserving task allocation for mobile crowdsensing. IEEE Transactions on Mobile Computing 18, 6 (2019), 1330--1341.Google ScholarDigital Library
- Z. Wang, X. Pang, Y. Chen, H. Shao, Q. Wang, L. Wu, H. Chen, and H. Qi. 2019a. Privacy-preserving crowd-sourced statistical data publishing with an untrusted server. IEEE Transactions on Mobile Computing 18, 6 (2019), 1356--1367.Google ScholarDigital Library
- Z. Wang, X. Pang, J. Hu, W. Liu, Q. Wang, Y. Li, and H. Chen. 2019b. When mobile crowdsensing meets privacy. IEEE Communications Magazine 57, 9 (2019), 72--78.Google ScholarDigital Library
- Z. Wang, M. Song, Z. Zhang, Y. Song, Q. Wang, and H. Qi. 2019c. Beyond inferring class representatives: User-level privacy leakage from federated learning. In Proceedings of the IEEE INFOCOM Conference.Google Scholar
- Hai-Qin Wu, Liangmin Wang, and Guoliang Xue. 2019. Privacy-aware task allocation and data aggregation in fog-assisted spatial crowdsourcing. IEEE Transactions on Network Science and Engineering 7, 1 (2019), 589--602.Google ScholarCross Ref
- D. Yuan, Q. Li, G. Li, Q. Wang, and K. Ren. 2020. PriRadar: A privacy-preserving framework for spatial crowdsourcing. IEEE Transactions on Information Forensics and Security 15 (2020), 299--314.Google ScholarDigital Library
- Lan Zhang, Xiang-Yang Li, and Yunhao Liu. 2013a. Message in a sealed bottle: Privacy preserving friending in social networks. In Proceedings of the 2013 IEEE 33rd International Conference on Distributed Computing Systems (ICDCS’13).Google ScholarDigital Library
- R. Zhang, J. Shi, Y. Zhang, and C. Zhang. 2013b. Verifiable privacy-preserving aggregation in people-centric urban sensing systems. IEEE Journal on Selected Areas in Communications 31, 9 (2013), 268--278.Google ScholarCross Ref
- P. Zhao, H. Jiang, J. C. S. Lui, C. Wang, F. Zeng, F. Xiao, and Z. Li. 2018a. P3-LOC: A privacy-preserving paradigm-driven framework for indoor localization. IEEE/ACM Transactions on Networking 26, 6 (2018), 2856--2869.Google ScholarDigital Library
- Ping Zhao, Hongbo Jiang, Chen Wang, Haojun Huang, Gaoyang Liu, and Yang Yang. 2018b. On the performance of k-anonymity against inference attacks with background information. IEEE Internet of Things Journal 6, 1 (2018), 808--819.Google ScholarCross Ref
Index Terms
DAML: Practical Secure Protocol for Data Aggregation Based on Machine Learning
Recommendations
Aggregating privatized medical data for secure querying applications
Public and private organizations generate large amounts of data which they are happy to allow others to query as long as it is privatized. (One example is that of medical data which can be used for research purposes.) Aggregation of such data on a cloud ...
A New Sensitive Data Aggregation Scheme for Protecting Integrity in Wireless Sensor Networks
CIT '10: Proceedings of the 2010 10th IEEE International Conference on Computer and Information TechnologySince wireless sensor networks (WSNs) are resources- constrained, it is very essential to gather data efficiently so that the life of the networks can be prolonged. Data aggregation can conserve a significant amount of energy by minimizing the ...
Scalability in Privacy-Preserving Data Aggregation for Wireless Sensor Networks
ISPA '10: Proceedings of the International Symposium on Parallel and Distributed Processing with ApplicationsIn this paper, we propose a new privacy preserving data aggregation scheme for WSNs. Our scheme applies additive property of complex numbers in order to combine sensor data and preserve data privacy during transmission to the sink node. In addition, for ...
Comments