Abstract
Over the years, the flourish of crowd computing has enabled enterprises to accomplish computing tasks through crowdsourcing in a large-scale and high-quality manner, and therefore how to efficiently and securely implement crowd computing becomes a hotspot. Some recent work innovatively adopted a P2P (peer-to-peer) network as the communication environment of crowdsourcing. Based on its decentralized control, issues like single-point-of-failure or DDoS attack can be overcome to some extent, but the huge computing capacity and storage costs required by this scheme is always unbearable. Federated learning is a distributed machine learning that supports local storage of data, and clients implement training through interactive gradient values. In our work, we combine blockchain with federated learning and propose a crowdsourcing framework named CrowdSFL, that users can implement crowdsourcing with less overhead and higher security. In addition, to protect the privacy of participants, we design a new re-encryption algorithm based on Elgamal to ensure that interactive values and other information will not be exposed to other participants outside the workflow. Finally, we have proved through experiments that our framework is superior to some similar work in accuracy, efficiency, and overhead.
Highlights
The concept of crowdsourcing has come a long way in the 14 years since it was first proposed by Jeff Howe in 2006
Inspired by previous related work, the CrowdSFL we proposed in this paper adopts the same storage strategy as [27], while using the original re-encryption algorithm to protect the confidentiality and anonymity of data
Evaluation Mechanism In Step 7 and Step 8, REQ and crowdsourcing platform (CSP) will work together to obtain a list of models that will participate in the aggregation
Summary
The concept of crowdsourcing has come a long way in the 14 years since it was first proposed by Jeff Howe in 2006. The earliest definition of crowdsourcing is the practice of a company or organization to outsource the tasks, usually performed by employees, to non-specific (and usually large) Internet crowds in a free and voluntary manner. Crowdsourcing tasks usually rely on human knowledge and intelligence. If it involves tasks that require many complex calculations, that is, crowd computing, it may rely on computing devices like CPUs. At present, crowdsourcing is actively developing, ranging from the analysis of big data [2] to the location service [3]. Some enterprises such as CrowdSpring, Uber, and Upwork are working hard to explore new working models and layouts for crowdsourcing
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have