Towards Data Poisoning Attacks in Crowd Sensing Systems
Abstract
With the proliferation of sensor-rich mobile devices, crowd sensing has emerged as a new paradigm of collecting information from the physical world. However, the sensory data provided by the participating workers are usually not reliable. In order to identify truthful values from the crowd sensing data, the topic of truth discovery, whose goal is to estimate each worker's reliability and infer the underlying truths through weighted data aggregation, is widely studied. Since truth discovery incorporates workers' reliability into the aggregation procedure, it shows robustness to the data poisoning attacks, which are usually conducted by the malicious workers who aim to degrade the effectiveness of the crowd sensing systems through providing malicious sensory data. However, truth discovery is not perfect in all cases. In this paper, we study how to effectively conduct two types of data poisoning attacks, i.e., the availability attack and the target attack, against a crowd sensing system empowered with the truth discovery mechanism. We develop an optimal attack framework in which the attacker can not only maximize his attack utility but also disguise the introduced malicious workers as normal ones such that they cannot be detected easily. The desirable performance of the proposed framework is verified through extensive experiments conducted on a real-world crowd sensing system.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
The GAN attack allows a malicious participant to train a GAN to generate prototypical samples of the targeted private training data.
“The GAN attack exploits the real-time nature of the FL learning process which allows the adversarial participant to train a GAN to generate prototypical samples of the targeted private training data.”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [76]
Cites
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075 · see citing works
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,863 · see citing works
Bertsekas, D. P. (1997) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600425 · Cited by 11,969 · see citing works
False data injection attacks against state estimation in electric power grids
Liu, Y., Ning, P., & Reiter, M. K. (2011) · ACM Transactions on Information and System Security · doi:10.1145/1952982.1952995 · Cited by 2,469 · see citing works
Poisoning Attacks against Support Vector Machines
Biggio, B., Nelson, B., & Laskov, P. (2012) · arXiv · doi:10.48550/arxiv.1206.6389 · Cited by 1,331 · see citing works
Huang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D. (2011) · Proceedings of the 4th ACM workshop on Security and artificial intelligence · doi:10.1145/2046684.2046692 · Cited by 1,194 · see citing works
Yang, D., Xue, G., Fang, X., & Tang, J. (2012) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/2348543.2348567 · Cited by 995 · see citing works
Practical Bilevel Optimization: Algorithms and Applications
Bard, J. F. (1998) · Nonconvex optimization and its applications · doi:10.1007/978-1-4757-2836-1 · Cited by 932 · see citing works
Can machine learning be secure?
Barreno, M., Nelson, B. A., Sears, R., Joseph, A. D., & Tygar, J. D. (2006) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/1128817.1128824 · Cited by 852 · see citing works
Resolving conflicts in heterogeneous data by truth discovery and source reliability estimation
Li, Q., Li, Y., Gao, J., Zhao, B., Fan, W., & Han, J. (2014) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/2588555.2610509 · Cited by 520 · see citing works
Self-citationIncentive Mechanisms for Crowdsensing: Crowdsourcing With Smartphones
Yang, D., Xue, G., Fang, X., & Tang, J. (2015) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2015.2421897 · Cited by 436 · see citing works
Li, Y., Gao, J., Meng, C., Li, Q., Su, L., Zhao, B., Fan, W., & Han, J. (2016) · ACM SIGKDD Explorations Newsletter · doi:10.1145/2897350.2897352 · Cited by 428 · see citing works
Self-citationSybil Attacks and Their Defenses in the Internet of Things
Zhang, K., Liang, X., Lu, R., & Shen, X. (2014) · IEEE Internet of Things Journal · doi:10.1109/jiot.2014.2344013 · Cited by 403 · see citing works
A confidence-aware approach for truth discovery on long-tail data
Li, Q., Li, Y., Gao, J., et al. (2014) · Proceedings of the VLDB Endowment · doi:10.14778/2735496.2735505 · Cited by 362 · see citing works
Self-citationCollaborative Spectrum Sensing in the Presence of Byzantine Attacks in Cognitive Radio Networks
Rawat, A. S., Anand, P., Chen, H., et al. (2010) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2010.2091277 · Cited by 326 · see citing works
Is feature selection secure against training data poisoning?Preprint
Huang, X. X., Biggio, B., Gavin Brown, B., Fumera, G., Eckert, C. M., & Roli, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.07933 · Cited by 310 · see citing works
Understanding Malicious Behavior in Crowdsourcing Platforms
Gadiraju, U., Kawase, R., Dietze, S., & Demartini, G. (2015) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702443 · Cited by 241 · see citing works
Data poisoning attacks on factorization-based collaborative filtering
Li, B., Wang, Y., Singh, A., & Vorobeychik, Y. (2016) · arXiv · doi:10.48550/arxiv.1608.08182 · Cited by 235 · see citing works
Providing long-term participation incentive in participatory sensing
Gao, L. X., Hou, F., & Huang, J. (2015) · doi:10.1109/infocom.2015.7218673 · Cited by 209 · see citing works
Data Poisoning Attacks against Autoregressive Models
Alfeld, S., Zhu, X., & Barford, P. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10237 · Cited by 205 · see citing works
Secure Data Aggregation Technique for Wireless Sensor Networks in the Presence of Collusion Attacks
Rezvani, M., Ignjatović, A., Bertino, E., et al. (2014) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2014.2316816 · Cited by 195 · see citing works
On Designing Data Quality-Aware Truth Estimation and Surplus Sharing Method for Mobile Crowdsensing
Yang, S., Wu, F., Tang, S., Gao, X., Yang, B., & Chen, G. (2017) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2017.2676898 · Cited by 186 · see citing works
Hu, S., Su, L., Liu, H., Wang, H., & Abdelzaher, T. (2015) · ACM Transactions on Sensor Networks · doi:10.1145/2770876 · Cited by 182 · see citing works
Self-citationCloud-Enabled Privacy-Preserving Truth Discovery in Crowd Sensing Systems
Miao, C., Jiang, W., Su, L., et al. (2015) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/2809695.2809719 · Cited by 169 · see citing works
Self-citationData Quality Guided Incentive Mechanism Design for Crowdsensing
Peng, D., Wu, F., & Chen, G. (2017) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2017.2714668 · Cited by 147 · see citing works
Man vs. machine: practical adversarial detection of malicious crowdsourcing workers
Wang, G., Wang, T., Zhang, H., & Zhao, B. Y. (2014) · Cited by 142 · see citing works
Conflicts to Harmony: A Framework for Resolving Conflicts in Heterogeneous Data by Truth Discovery
Li, Y., Li, Q., Gao, J., et al. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2016.2559481 · Cited by 127 · see citing works
Self-citationDefending against Sybil Devices in Crowdsourced Mapping Services
Wang, G., Wang, B., Wang, T., Nika, A., Zheng, H.-T., & Zhao, B. Y. (2016) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/2906388.2906420 · Cited by 108 · see citing works
Context-aware data quality estimation in mobile crowdsensing
Liu, S., Zheng, Z., Wu, F., et al. (2017) · doi:10.1109/infocom.2017.8057033 · Cited by 89 · see citing works
Detecting Malicious Data Injections in Wireless Sensor Networks
Illiano, V. P., & Lupu, E. (2015) · ACM Computing Surveys · doi:10.1145/2818184 · Cited by 80 · see citing works
(2006) · Springer eBooks · doi:10.1007/3-540-31008-8 · Cited by 77 · see citing works
Scalable Mobile Crowdsensing via Peer-to-Peer Data Sharing
Jiang, C., Gao, L. X., Duan, L., et al. (2017) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2017.2743718 · Cited by 74 · see citing works
Towards Cyber-Physical Systems in Social Spaces: The Data Reliability Challenge
Wang, S., Wang, D., Su, L., Kaplan, L., & Abdelzaher, T. (2014) · IEEE Real-Time Systems Symposium (RTSS) · doi:10.1109/rtss.2014.19 · Cited by 72 · see citing works
Self-citationAttack Prevention for Collaborative Spectrum Sensing in Cognitive Radio Networks
Duan, L., Min, E., Member, S., et al. (2013) · Cited by 70 · see citing works
Cooperative Defense Against Pollution Attacks in Network Coding Using SpaceMac
Le, A., & Markopoulou, A. P. (2012) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2012.120224 · Cited by 60 · see citing works
Miao, C., Li, Q., Su, L., Huai, M., Jiang, W., & Gao, J. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186032 · Cited by 59 · see citing works
Self-citationSecure crowdsourcing-based cooperative pectrum sensing
Zhang, R., Zhang, J., Zhang, Y., et al. (2013) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infcom.2013.6567059 · Cited by 54 · see citing works
Reputation-based Worker Filtering in Crowdsourcing
Jagabathula, S., Subramanian, L., & Venkataraman, A. (2014) · neural information processing systems · Cited by 53 · see citing works
Scalable social sensing of interdependent phenomena
Wang, S., Su, L., Shen, L., et al. (2015) · International Conference on Information Processing in Sensor Networks (IPSN) · doi:10.1145/2737095.2737114 · Cited by 53 · see citing works
Self-citationGeneralized Decision Aggregation in Distributed Sensing Systems
Su, L., Li, Q., Hu, S., et al. (2014) · Proceedings/Proceedings - Real-Time Systems Symposium · doi:10.1109/rtss.2014.40 · Cited by 52 · see citing works
Self-citationThwarting Intelligent Malicious Behaviors in Cooperative Spectrum Sensing
Wang, W., Chen, L., Shin, K. G., et al. (2015) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2015.2398446 · Cited by 47 · see citing works
Defending Against Cooperative Attacks in Cooperative Spectrum Sensing
Qin, Z., Li, Q., & Hsieh, G. (2013) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2013.041913.120516 · Cited by 47 · see citing works
Self-citationRobust Collaborative Spectrum Sensing Schemes for Cognitive Radio Networks
Li, H., Cheng, X., Li, K., Hu, C., Zhang, N., & Xue, W. (2013) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2013.73 · Cited by 34 · see citing works
Privacy-Preserving Crowdsensing: Privacy Valuation, Network Effect, and Profit Maximization
Zhang, M., Yang, L., Gong, X., et al. (2016) · Globecom · doi:10.1109/glocom.2016.7842170 · Cited by 28 · see citing works
Protecting Mobile Crowd Sensing against Sybil Attacks Using Cloud Based Trust Management System
Chang, S., & Chen, Z. (2016) · Mobile Information Systems · doi:10.1155/2016/6506341 · Cited by 25 · see citing works
Combating Software and Sybil Attacks to Data Integrity in Crowd-Sourced Embedded Systems
Dua, A., Bulusu, N., Feng, W.-C., et al. (2014) · ACM Transactions on Embedded Computing Systems · doi:10.1145/2629338 · Cited by 8 · see citing works
Scalable Mobile Crowdsensing via Peer-to-Peer Data SharingPreprint
Jiang, C., Gao, L. X., Duan, L., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.05343 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Privacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548 · see citing works
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Goldblum, M., Tsipras, D., Xie, C., Chen, X., Schwarzschild, A., Song, D., Madry, A., Li, B., & Goldstein, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3162397 · Cited by 362 · see citing works
- Authors
- Miao, C., Li, Q., Xiao, H., Jiang, W., Huai, M., & Su, L.
- Affiliations
- University at Buffalo, State University of New York (US)
- University of Illinois Urbana-Champaign (US)
- State University of New York at Buffalo, NY, USA
- Venue
- Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing
- Publisher
- ACM
- Published
- 2018-06-26
- Pages
- 111-120
- OpenAlex
- W2809622771
- Cited by
- 77
- References
- 47
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 7 · 2023: 9 · 2022: 12 · 2021: 13 · 2020: 19 · 2019: 9
- FWCI
- 11.63
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc) (publishedVersion)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Computer Science Applications › Mobile Crowdsensing and Crowdsourcing
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- data poisoning, crowdsensing, truth discovery, malicious workers, attack detection evasion
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
