ABSTRACT
Crowd-powered systems have become a popular way to augment the capabilities of automated systems in real-world settings. Many of these systems rely on human workers to process potentially sensitive data or make important decisions. This puts these systems at risk of unintentionally releasing sensitive data or having their outcomes maliciously manipulated. While almost all crowd-powered approaches account for errors made by individual workers, few factor in active attacks on the system. In this paper, we analyze different forms of threats from individuals and groups of workers extracting information from crowd-powered systems or manipulating these systems' outcomes. Via a set of studies performed on Amazon's Mechanical Turk platform and involving 1,140 unique workers, we demonstrate the viability of these threats. We show that the current system is vulnerable to coordinated attacks on a task based on the requests of another task and that a significant portion of Mechanical Turk workers are willing to contribute to an attack. We propose several possible approaches to mitigating these threats, including leveraging workers who are willing to go above and beyond to help, automatically flagging sensitive content, and using workflows that conceal information from each individual, while still allowing the group to complete a task. Our findings enable the crowd to continue to play an important part in automated systems, even as the data they use and the decisions they support become increasingly important.
- Bernstein, M.S., Brandt, J.R., Miller, R.C. and Karger, D.R. Crowds in two seconds: Enabling realtime crowdpowered interfaces. In Proceedings of UIST 2011. Google ScholarDigital Library
- Bernstein, M.S., Little, G., Miller, R.C., Hartmann, B., Ackerman, M.S., Karger, D.R., Crowell, D. and Panovich, K. Soylent: A word processor with a crowd inside. In Proceedings of UIST 2010. Google ScholarDigital Library
- Bigham, J.P., Jayant, C., Ji, H., Little, G., Miller, A., Miller, R.C., Miller, R., Tatarowicz, A., White, B., White, S. and Yeh, T. VizWiz: nearly real-time answers to visual questions. In Proceedings of UIST 2010. Google ScholarDigital Library
- Chen, X., Bennett, P.N., Collins-Thompson, K. and Horvitz, E. Pairwise ranking aggregation in a crowdsourced setting. In Proceedings of WSDM 2013. Google ScholarDigital Library
- Deng, J., Krause, J., and Fei-Fei, L. Fine-Grained Crowdsourcing for Fine-Grained Recognition. In Proceesings of CVPR 2013. Google ScholarDigital Library
- Evanini, K. and Zechner, K. Using crowdsourcing to provide prosodic annotations for non-native speech. In Proceedings of Interspeech 2011.Google ScholarCross Ref
- Featured requester: Discover how comScore benefits from mechanical Turk. The Mechanical Turk Blog, March 2013. http://bit.ly/Ye64SbGoogle Scholar
- Harris, Christopher G. Dirty Deeds Done Dirt Cheap: A Darker Side to Crowdsourcing. In SocialCom 2011.Google ScholarCross Ref
- Kamar, E., Hacker, S., Lintott, C. and Horvitz, E. Combining human and machine learning intelligence in large-scale crowdsourcing: Principles, methods, and studies. MSR-TR-2012-58, 2012.Google Scholar
- Kittur, A. and Kraut, R.E. Harnessing the wisdom of crowds in Wikipedia: Quality through coordination. In Proceedings of CSCW 2008. Google ScholarDigital Library
- Kittur, A., Nickerson, J.V., Bernstein, M., Gerber, E., Shaw, A., Zimmerman, J., Lease, M., and Horton, J. The future of crowd work. In Proceedings of CSCW 2013. Google ScholarDigital Library
- Kokkalis, N., Köhn, T., Pfeiffer, C., Chornyi, D., Bernstein, M.S. and Klemmer, S.R. EmailValet: Managing email overload through private, accountable crowdsourcing. In Proceedings of CSCW 2013. Google ScholarDigital Library
- Le, J., Edmonds, A., Hester,V., and Biewald, L. Ensuring quality in crowdsourced search relevance evaluation. In Proceedings of SIGIR 2010 Workshop on Crowdsourcing for Search Evaluation.Google Scholar
- Little, G., Chilton, L.B., Goldman, M. and Miller, R.C. TurKit: Human computation algorithms on mechanical turk. In Proceedings of UIST 2010. Google ScholarDigital Library
- Little, G. and Sun, Y-A. Human OCR. CHI 2011 Workshop on Crowdsourcing and Human Computation.Google Scholar
- Lasecki, W.S., Miller, C., Sadilek, A., Abumoussa, A., Borrello, D., Kushalnagar, R. and Bigham, J.P. Realtime captioning by groups of non-experts. In Proceedings of UIST 2012. Google ScholarDigital Library
- Lasecki, W.S., Murray, K.I., White, S., Miller, R.C. and Bigham, J.P. Real-time crowd control of existing interfaces. In Proceedings of UIST 2011. Google ScholarDigital Library
- Lasecki, W.S., Song, Y.C., Kautz, H. and Bigham, J.P. Real-time crowd labeling for deployable activity recognition. In Proceedings CSCW 2013. Google ScholarDigital Library
- Lasecki, W.S., Thiha, P., Zhong, Y., Brady, E. and Bigham, J.P. Answering Visual Questions with Conversational Crowd Assistants. In Proceedings of ASSETS 2013. Google ScholarDigital Library
- Lasecki, W.S., Wesley, R., Nichols, J., Kulkari, A., Allen, J.F. and Bigham, J.P. Chorus: A Crowd-Powered Personal Assistant. In Proceedings of UIST 2013. Google ScholarDigital Library
- Lasecki, W.S., White, S.C., Murray, K.I. and Bigham, J.P. Crowd Memory: Learning in the collective. In Proceedings of Collective Intelligence 2012.Google Scholar
- Mason, W. and Watts, D.J. Financial incentives and the performance of crowds. In Proceedings of HComp 2009. Google ScholarDigital Library
- Massively multiplayer pong. http://collisiondetection.net, 2006.Google Scholar
- Menton, C. and Singh, P. Manipulation can be hard in tractable voting systems even for constant-sized coalitions. CoRR abs/1108.4439.Google Scholar
- Sun, Y-A. Roy, S. and Little, G. Beyond independent agreement: A tournament selection approach for quality assurance of human computation tasks. In HComp 2011.Google Scholar
- Sweeney, L. Uniqueness of simple demographics in the U.S. population. In LIDAP-WP4, Carnegie Mellon University. 2000.Google Scholar
- Quinn, A.J. and Bederson, B.B. Human computation: A survey and taxonomy of a growing field. In Proceedings of CHI 2011. Google ScholarDigital Library
- Van Boskrik, S. US interactive marketing forecast, 2011 to 2016. Forrester. August 2011.Google Scholar
- Von Ahn, L. Games with a purpose. Comp. 39(6), 2006.Google Scholar
- Zaidan, O.F. and Callison-Burch, C. Crowdsourcing translation: professional quality from non-professionals. In Proceedings of ACL-HLT 2011. Google ScholarDigital Library
Index Terms
- Information extraction and manipulation threats in crowd-powered systems
Recommendations
"Our Privacy Needs to be Protected at All Costs": Crowd Workers' Privacy Experiences on Amazon Mechanical Turk
Crowdsourcing platforms such as Amazon Mechanical Turk (MTurk) are widely used by organizations, researchers, and individuals to outsource a broad range of tasks to crowd workers. Prior research has shown that crowdsourcing can pose privacy risks (e.g., ...
Modus Operandi of Crowd Workers: The Invisible Role of Microtask Work Environments
The ubiquity of the Internet and the widespread proliferation of electronic devices has resulted in flourishing microtask crowdsourcing marketplaces, such as Amazon MTurk. An aspect that has remained largely invisible in microtask crowdsourcing is that ...
Make Hay While the Crowd Shines: Towards Efficient Crowdsourcing on the Web
WWW '15 Companion: Proceedings of the 24th International Conference on World Wide WebWithin the scope of this PhD proposal, we set out to investigate two pivotal aspects that influence the effectiveness of crowdsourcing: (i) microtask design, and (ii) workers behavior. Leveraging the dynamics of tasks that are crowdsourced on the one ...
Comments