LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Service Integrity Assurance for Distributed Computation Outsourcing

Photo by impatrickt from unsplash

In this paper, we propose a method to ensure service integrity for distributed computation outsourcing in different contexts, such as volunteer computing, grid computing, MapReduce computing, and crowdsourcing. We propose… Click to show full abstract

In this paper, we propose a method to ensure service integrity for distributed computation outsourcing in different contexts, such as volunteer computing, grid computing, MapReduce computing, and crowdsourcing. We propose replicating the computations among multiple workers and manipulating the input of the replicated computations by mixing or adding noise. The idea of manipulating the inputs of the replicated computations, which is introduced in this paper for the first time, prevents attacks made by cheater or malicious workers, even in the case of collusion among these workers. By mixing inputs, collusive cheater workers are prevented from easily detecting replication; thus, they do not return random or partial results as output. Adding noise to the inputs prevents cheater and malicious workers from detecting replication, even in the case of collusion among workers. Therefore, they do not return incorrect output. To evaluate the proposed method, we adopt a game-theoretic approach. We also provide a simulation environment to evaluate the overhead of the proposed method. We demonstrate that the proposed method can guarantee high accuracy with low overhead, even when malicious workers constitute the majority of the workers. For instance, the proposed method can ensure high accuracy with 61.27 percent overhead in the case of 60 percent malicious workers.

Keywords: proposed method; service integrity; computation outsourcing; distributed computation; malicious workers

Journal Title: IEEE Transactions on Services Computing
Year Published: 2020

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.