TY - GEN
T1 - Traffic Correlation for Deanonymizing Cryptocurrency Wallet Through Tor
AU - Kong, Xiangdong
AU - Shen, Meng
AU - Che, Zheng
AU - Yu, Congcong
AU - Zhu, Liehuang
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2022
Y1 - 2022
N2 - Cryptocurrencies have increasingly become the preferred choice for private transactions due to their anonymity and decentralized features. When a user creates transactions using wallet software with built-in Tor module, their identity information is further protected. At the same time, however, this combination of Tor and cryptocurrency is misused to carry out illegal acts, while the perpetrators are difficult to detect. Therefore, it is important to study traffic correlation methods for cryptocurrencies over Tor to maintain a healthy blockchain ecosystem. In this paper, based on existing work, we propose CryptoCorr, a traffic analysis model for cryptocurrency wallets, which can screening the collected Tor traffic data based on time window and flow features, and implement traffic correlation for cryptocurrency wallets based on deep learning architecture. We validate the proposed model by constructing a dataset with 82077 collected packets of wallet, and the experiment results demonstrate the effectiveness of the CryptoCorr model.
AB - Cryptocurrencies have increasingly become the preferred choice for private transactions due to their anonymity and decentralized features. When a user creates transactions using wallet software with built-in Tor module, their identity information is further protected. At the same time, however, this combination of Tor and cryptocurrency is misused to carry out illegal acts, while the perpetrators are difficult to detect. Therefore, it is important to study traffic correlation methods for cryptocurrencies over Tor to maintain a healthy blockchain ecosystem. In this paper, based on existing work, we propose CryptoCorr, a traffic analysis model for cryptocurrency wallets, which can screening the collected Tor traffic data based on time window and flow features, and implement traffic correlation for cryptocurrency wallets based on deep learning architecture. We validate the proposed model by constructing a dataset with 82077 collected packets of wallet, and the experiment results demonstrate the effectiveness of the CryptoCorr model.
KW - CryptoCurrency
KW - Deanonymizing
KW - Tor
KW - Traffic analysis
KW - Wallet RPC
UR - http://www.scopus.com/inward/record.url?scp=85145250779&partnerID=8YFLogxK
U2 - 10.1007/978-981-19-8043-5_21
DO - 10.1007/978-981-19-8043-5_21
M3 - Conference contribution
AN - SCOPUS:85145250779
SN - 9789811980428
T3 - Communications in Computer and Information Science
SP - 292
EP - 305
BT - Blockchain and Trustworthy Systems - 4th International Conference, BlockSys 2022, Revised Selected Papers
A2 - Svetinovic, Davor
A2 - Zhang, Yin
A2 - Huang, Xiaoyan
A2 - Luo, Xiapu
A2 - Chen, Xingping
PB - Springer Science and Business Media Deutschland GmbH
T2 - 4th International Conference on Blockchain and Trustworthy Systems, Blocksys 2022
Y2 - 4 August 2022 through 5 August 2022
ER -