Can Ozturan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Can Ozturan has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Gunhan Dundar
Department of Electrical and Electronics Engineering, Bogazici University, Bebek, Istanbul, Turkey
4 shared publications Seren Soner
Computer Engineering Department; Bogazici University; Istanbul Turkey
4 shared publications- Ali Haydar Özer
Department of Computer Engineering Faculty of Engineering, Marmara University Istanbul Turkey
3 shared publications - Alper Sen
Boğaziçi University
3 shared publications Kubilay Atasu
IBM Research¿Zurich
3 shared publications- Alper Alimoglu
Department of Computer Engineering Bogazici University Istanbul Turkey
2 shared publications
Latest Publications
- 25 November 2024
- Published by Elsevier in Computer Communications
- Vol. 230
Trustless privacy-preserving data aggregation on Ethereum with hypercube network topology
- 25 November 2024
- Published by Elsevier in Computer Communications
- Vol. 230
Trustless privacy-preserving data aggregation on Ethereum with hypercube network topology
- Open Access
- 18 March 2024
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 36 (13) , e8087
An autonomous blockchain‐based computational broker for e‐science
Blockchain infrastructures have emerged as a disruptive technology and have led to the realization of cryptocurrencies (peer‐to‐peer payment systems) and smart contracts. They can have a wide range of application areas in e‐Science due to their open, public nature and global accessability in a trustless manner. We propose and implement a smart contract called eBlocBroker, which is an autonomous blockchain‐based middleware system for volunteer computing and providing data resources for e‐Science. The eBlocBroker infrastructure connects requesters who need to combine applications (jobs) with datasets and run them via an Ethereum‐based private blockchain network (Bloxberg) on providers that utilize computational and data resources on clouds or home servers. It uses cloud storage, such as B2DROP, IPFS, or Google Drive, to store and transfer data between requesters and providers. Each provider utilizes the Slurm workload manager to execute jobs submitted through eBlocBroker. In this paper, we demonstrate how an autonomous organization programmed as a smart contract can be used to deploy a marketplace that supports data and computation‐intensive research projects. We propose a cost model implemented as a function in the smart contract which calculates and records computation and dataset usage costs. We develop a Python‐based system to communicate with eBlocBroker and orchestrate jobs' execution on the provider's end. We present eBlocBroker's features, infrastructure, implementation, algorithms and experimental results.
- 18 March 2024
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 36 (13) , e8087
Open AccessAn autonomous blockchain‐based computational broker for e‐science
Blockchain infrastructures have emerged as a disruptive technology and have led to the realization of cryptocurrencies (peer‐to‐peer payment systems) and smart contracts. They can have a wide range of application areas in e‐Science due to their open, public nature and global accessability in a trustless manner. We propose and implement a smart contract called eBlocBroker, which is an autonomous blockchain‐based middleware system for volunteer computing and providing data resources for e‐Science. The eBlocBroker infrastructure connects requesters who need to combine applications (jobs) with datasets and run them via an Ethereum‐based private blockchain network (Bloxberg) on providers that utilize computational and data resources on clouds or home servers. It uses cloud storage, such as B2DROP, IPFS, or Google Drive, to store and transfer data between requesters and providers. Each provider utilizes the Slurm workload manager to execute jobs submitted through eBlocBroker. In this paper, we demonstrate how an autonomous organization programmed as a smart contract can be used to deploy a marketplace that supports data and computation‐intensive research projects. We propose a cost model implemented as a function in the smart contract which calculates and records computation and dataset usage costs. We develop a Python‐based system to communicate with eBlocBroker and orchestrate jobs' execution on the provider's end. We present eBlocBroker's features, infrastructure, implementation, algorithms and experimental results.
- 6 October 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 151, 260-271
Quantised and Simulated Max–min Fairness in Blockchain Ecosystems
- 6 October 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 151, 260-271
Quantised and Simulated Max–min Fairness in Blockchain Ecosystems
- Open Access
- 4 January 2022
- Published by Springer Nature in Cluster Computing
- Vol. 25 (3) , 1885-1898
Parallel analysis of Ethereum blockchain transaction data using cluster computing
Ability to perform fast analysis on massive public blockchain transaction data is needed in various applications such as tracing fraudulent financial transactions. The blockchain data is continuously growing and is organized as a sequence of blocks containing transactions. This organization, however, cannot be used for parallel graph algorithms which need efficient distributed graph data structures. Using message passing libraries (MPI), we develop a scalable cluster-based system that constructs a distributed transaction graph in parallel and implement various transaction analysis algorithms. We report performance results from our system operating on roughly 5 years of 10.2 million block Ethereum Mainnet blockchain data. We report timings obtained from tests involving distributed transaction graph construction, partitioning, page ranking of addresses, degree distribution, token transaction counting, connected components finding and our new parallel blacklisted address trace forest computation algorithm on a 16 node economical cluster set up on the Amazon cloud. Our system is able to construct a distributed graph of 766 million transactions in 218 s and compute the forest of blacklisted address traces in 32 s.
- 4 January 2022
- Published by Springer Nature in Cluster Computing
- Vol. 25 (3) , 1885-1898
Open AccessParallel analysis of Ethereum blockchain transaction data using cluster computing
Ability to perform fast analysis on massive public blockchain transaction data is needed in various applications such as tracing fraudulent financial transactions. The blockchain data is continuously growing and is organized as a sequence of blocks containing transactions. This organization, however, cannot be used for parallel graph algorithms which need efficient distributed graph data structures. Using message passing libraries (MPI), we develop a scalable cluster-based system that constructs a distributed transaction graph in parallel and implement various transaction analysis algorithms. We report performance results from our system operating on roughly 5 years of 10.2 million block Ethereum Mainnet blockchain data. We report timings obtained from tests involving distributed transaction graph construction, partitioning, page ranking of addresses, degree distribution, token transaction counting, connected components finding and our new parallel blacklisted address trace forest computation algorithm on a 16 node economical cluster set up on the Amazon cloud. Our system is able to construct a distributed graph of 766 million transactions in 218 s and compute the forest of blacklisted address traces in 32 s.
- Open Access
- 24 December 2021
- Published by Springer Nature
- p. 253-267
Analyzing Large-Scale Blockchain Transaction Graphs for Fraudulent Activities
Early public blockchains provided low transaction throughputs in the range of 7–30 transactions per second. With the emergence of permissioned and proof-of-stake-based blockchains, transaction throughputs are expected to rise drastically to thousands per second. Blockchain transactions form directed graphs. With high transaction throughputs and growing blockchain adoption by banks, businesses and customers in general, the number of edges in transaction graphs will dynamically grow to billions. An analysis of large-scale transaction graphs is needed for tracing fraudulent activities on blockchains. This chapter will cover topics such as distributed graph data structures, the use of message passing libraries, and parallel graph algorithms in order to build a scalable transaction graph analysis system. Results from the analysis of the real Ethereum and Bitcoin public blockchain data involving cryptocurrency and ERC20 token transactions will be presented.
- 24 December 2021
- Published by Springer Nature
- p. 253-267
Open AccessAnalyzing Large-Scale Blockchain Transaction Graphs for Fraudulent Activities
Early public blockchains provided low transaction throughputs in the range of 7–30 transactions per second. With the emergence of permissioned and proof-of-stake-based blockchains, transaction throughputs are expected to rise drastically to thousands per second. Blockchain transactions form directed graphs. With high transaction throughputs and growing blockchain adoption by banks, businesses and customers in general, the number of edges in transaction graphs will dynamically grow to billions. An analysis of large-scale transaction graphs is needed for tracing fraudulent activities on blockchains. This chapter will cover topics such as distributed graph data structures, the use of message passing libraries, and parallel graph algorithms in order to build a scalable transaction graph analysis system. Results from the analysis of the real Ethereum and Bitcoin public blockchain data involving cryptocurrency and ERC20 token transactions will be presented.
- 20 October 2021
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 34 (4) , e6659
Parallel network simplex algorithm for the minimum cost flow problem
In this work, we contribute a parallel implementation of the network simplex algorithm that is used for the solution of minimum cost flow problem. In the network simplex algorithm, finding an entering arc requires searching through many arcs to decide which one should be included in the spanning tree solution on the next iteration. We propose finding the entering arc in parallel as it often takes the majority of the execution time. A usual strategy is to pick the arc violating the optimality the most out of all possible candidates. Scanning all arcs can take quite some time, so it is common to consider only a fixed number of arcs which is referred as the block search pivoting rule. Arc scans can easily be done in parallel to find the best candidate as the calculations are independent of each other. We used shared memory parallelism using OpenMP along with vectorization using AVX instructions. We also tried adjusting block sizes to increase the parallel portion of the algorithm. Our dataset consists of various natural and synthetic graphs with sizes up to a billion arc. Our experiments show speedups up to four are possible, though they are typically lower.
- 20 October 2021
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 34 (4) , e6659
Parallel network simplex algorithm for the minimum cost flow problem
In this work, we contribute a parallel implementation of the network simplex algorithm that is used for the solution of minimum cost flow problem. In the network simplex algorithm, finding an entering arc requires searching through many arcs to decide which one should be included in the spanning tree solution on the next iteration. We propose finding the entering arc in parallel as it often takes the majority of the execution time. A usual strategy is to pick the arc violating the optimality the most out of all possible candidates. Scanning all arcs can take quite some time, so it is common to consider only a fixed number of arcs which is referred as the block search pivoting rule. Arc scans can easily be done in parallel to find the best candidate as the calculations are independent of each other. We used shared memory parallelism using OpenMP along with vectorization using AVX instructions. We also tried adjusting block sizes to increase the parallel portion of the algorithm. Our dataset consists of various natural and synthetic graphs with sizes up to a billion arc. Our experiments show speedups up to four are possible, though they are typically lower.
- 2 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 59-65
A Cluster Based System for Analyzing Ethereum Blockchain Transaction Data
Ability to perform fast analysis on massive public blockchain transaction data is needed in various finance applications such as tracing of fraudulent activities. The blockchain data that is synced as a node is accessible as a sequence of blocks containing transactions. This way of accessing transaction data, however, is too slow for applications that require a transaction graph to be constructed. We develop a cluster based system that constructs a distributed transaction graph in parallel. Since blockchain data is continuously growing, our parallel system also offers the advantage of being able to scale by simply increasing the number of nodes in the cluster. Our system has been developed using the MPI message passing interface. We report performance results from our system operating on the whole 9.5 million block (roughly 4 year) Ethereum mainnet blockchain data. We report timings obtained from tests involving distributed transaction graph construction, partitioning, page ranking of addresses, degree distribution and token transaction counting on a 16 node economical cluster set up on the Amazon cloud. In particular, our system is able to construct distributed graph of 658 million ether and 31 major token transactions in 188 seconds.
- 2 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 59-65
A Cluster Based System for Analyzing Ethereum Blockchain Transaction Data
Ability to perform fast analysis on massive public blockchain transaction data is needed in various finance applications such as tracing of fraudulent activities. The blockchain data that is synced as a node is accessible as a sequence of blocks containing transactions. This way of accessing transaction data, however, is too slow for applications that require a transaction graph to be constructed. We develop a cluster based system that constructs a distributed transaction graph in parallel. Since blockchain data is continuously growing, our parallel system also offers the advantage of being able to scale by simply increasing the number of nodes in the cluster. Our system has been developed using the MPI message passing interface. We report performance results from our system operating on the whole 9.5 million block (roughly 4 year) Ethereum mainnet blockchain data. We report timings obtained from tests involving distributed transaction graph construction, partitioning, page ranking of addresses, degree distribution and token transaction counting on a 16 node economical cluster set up on the Amazon cloud. In particular, our system is able to construct distributed graph of 658 million ether and 31 major token transactions in 188 seconds.
- Open Access
- 16 June 2020
- Published by University Library System, University of Pittsburgh in Ledger
- Vol. 5, 20-35
Barter Machine: An Autonomous, Distributed Barter Exchange on the Ethereum Blockchain
Direct bartering allows for the trading of assets with or without the use of money. In this paper, we introduce a smart contract written in the Solidity language for the Ethereum blockchain that implements a distributed and autonomous direct barter exchange operated by crowds. Since ERC20 smart contract tokens are widely used for initial coin offerings (ICOs), our implementation provides autonomous bartering services for ERC20 tokens. The non-fungible ERC721 token, as well as Ethereum Name Service (ENS) name bartering, are also supported. Because finding a feasible bartering solution for bids involving multiple tokens is NP-hard in general, our exchange only provides escrow and swapping services. It assumes feasible solutions are submitted by bartering problem solvers from the crowd who run a solver locally on their machines. Bartering problem solvers are incentivized to submit solutions to the autonomous exchange by awarding them with excess tokens that are left over after granting the bidders the tokens they requested in their bids. Our system, called BarterMachine, can perhaps be used to facilitate a global barter economy. The BarterMachine prototype is available for testing on the Ethereum Ropsten network at https://bartermachine.github.io/bartermachine/ropsten/.
- 16 June 2020
- Published by University Library System, University of Pittsburgh in Ledger
- Vol. 5, 20-35
Open AccessBarter Machine: An Autonomous, Distributed Barter Exchange on the Ethereum Blockchain
Direct bartering allows for the trading of assets with or without the use of money. In this paper, we introduce a smart contract written in the Solidity language for the Ethereum blockchain that implements a distributed and autonomous direct barter exchange operated by crowds. Since ERC20 smart contract tokens are widely used for initial coin offerings (ICOs), our implementation provides autonomous bartering services for ERC20 tokens. The non-fungible ERC721 token, as well as Ethereum Name Service (ENS) name bartering, are also supported. Because finding a feasible bartering solution for bids involving multiple tokens is NP-hard in general, our exchange only provides escrow and swapping services. It assumes feasible solutions are submitted by bartering problem solvers from the crowd who run a solver locally on their machines. Bartering problem solvers are incentivized to submit solutions to the autonomous exchange by awarding them with excess tokens that are left over after granting the bidders the tokens they requested in their bids. Our system, called BarterMachine, can perhaps be used to facilitate a global barter economy. The BarterMachine prototype is available for testing on the Ethereum Ropsten network at https://bartermachine.github.io/bartermachine/ropsten/.
- Open Access
- 9 December 2019
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 45 (4) , 1-28
Algorithm 1002
The maximum flow problem is one of the most common network flow problems. This problem involves finding the maximum possible amount of flow between two designated nodes on a network with arcs having flow capacities. The push-relabel algorithm is one of the fastest algorithms to solve this problem. We present a shared memory parallel push-relabel algorithm. Graph coloring is used to avoid collisions between threads for concurrent push and relabel operations. In addition, excess values of target nodes are updated using atomic instructions to prevent race conditions. The experiments show that our algorithm is competitive for wide graphs with low diameters. Results from three different data sets are included, computer vision problems, DIMACS challenge problems, and KaHIP partitioning problems. These are compared with existing push-relabel and pseudoflow implementations. We show that high speedup rates are possible using our coloring based parallelization technique on sparse networks. However, we also observe that the pseudoflow algorithm runs faster than the push-relabel algorithm on dense and long networks.
- 9 December 2019
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Mathematical Software
- Vol. 45 (4) , 1-28
Open AccessAlgorithm 1002
The maximum flow problem is one of the most common network flow problems. This problem involves finding the maximum possible amount of flow between two designated nodes on a network with arcs having flow capacities. The push-relabel algorithm is one of the fastest algorithms to solve this problem. We present a shared memory parallel push-relabel algorithm. Graph coloring is used to avoid collisions between threads for concurrent push and relabel operations. In addition, excess values of target nodes are updated using atomic instructions to prevent race conditions. The experiments show that our algorithm is competitive for wide graphs with low diameters. Results from three different data sets are included, computer vision problems, DIMACS challenge problems, and KaHIP partitioning problems. These are compared with existing push-relabel and pseudoflow implementations. We show that high speedup rates are possible using our coloring based parallelization technique on sparse networks. However, we also observe that the pseudoflow algorithm runs faster than the push-relabel algorithm on dense and long networks.