Cross-Domain Fraud Detection in Ethereum Tokens Using On-Chain Time Series Based on Neural Networks and Reservoir Computing

• Lívia Carrera IME https://orcid.org/0000-0001-5329-8080
• Raquel C.G. Pinto IME https://orcid.org/0000-0003-0593-8105
• Anderson Fernandes Pereira dos Santos IME / Venturus Innovation Center https://orcid.org/0000-0002-6754-4809

DOI: https://doi.org/10.5753/sbseg.2026.27637

Resumo

Fraud in Ethereum token launches (ICOs, IDOs, and NFTs) produces observable on-chain behavioral patterns: anomalous asset concentration, artificial participant influx, fee manipulation, and abrupt activity collapse. This paper investigates whether four time series used for ICO fraud detection act as transferable behavioral indicators across launch modalities. The main contribution is the cross-domain evaluation protocol itself, applied uniformly to all model families: we empirically evaluate it on 758 labeled assets (ICO, IDO, NFT), comparing Keras baselines (MLP, CNN-MLP, LSTM-MLP), classical Echo State Networks (ESN), and Quantum Reservoir Computing (QRC) under a unified fixed decision threshold (τ = 0.5). Performance is assessed with metrics robust to class imbalance (PR-AUC, ROC-AUC, F1, precision, recall) and a threshold-collapse diagnostic. IDO time series were fully extracted via Etherscan API v2; NFT reached 87.6% extraction coverage (219 of 250 labeled collections). Results show strong intra-domain predictivity across all three domains, but zero-shot transfer fails (ICO→IDO/NFT PR-AUC≈ 0.51, below the ≈ 0.60 random baseline expected at observed prevalence): behavioral invariance was not observed across the domains and fraud definitions considered in this study. ESN-fusion-matched achieved the best ICO discriminative ranking (PR-AUC= 0.808), with no significant difference between classical and quantum reservoirs under the paired statistical protocol.

Referências

Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., and Vaughan, J. W. (2010). A theory of learning from different domains. Machine Learning, 79(1–2):151–175.

Buterin, V. (2014). Ethereum: A next-generation smart contract and decentralized application platform. White Paper, Ethereum Foundation.

Cernera, F., La Morgia, M., Mei, A., and Sassi, F. (2023). Ready, aim, snipe! Analysis of sniper bots and their impact on the DeFi ecosystem. In Proceedings of the ACM Web Conference (WWW).

Chen, W., Zheng, Z., Cui, J., Ngai, E., Zheng, P., and Zhou, Y. (2018). Detecting Ponzi schemes on Ethereum: Towards healthier blockchain technology. In Proceedings of the 27th International Conference on World Wide Web (WWW), pages 1409–1418.

Chen, W., Zheng, Z., Ngai, E. C.-H., Zheng, P., and Zhou, Y. (2019). Exploiting blockchain data to detect smart Ponzi schemes on Ethereum. IEEE Access, 7:37575–37586.

da Mata Caffé, L. A. Z., Braga, R. Z., Júnior, L. A. P., de Azevedo Castro Cesar, C., and Marcondes, C. A. C. (2023). Detecção de fraudes em criptomoedas utilizando métodos de classificação de séries temporais baseados em redes neurais. In Anais do XXIII Simpósio Brasileiro de Cibersegurança (SBSeg), pages 484–497, Juiz de Fora/MG. SBC.

dos Santos, A. F. P. (2026). QRC-Lab: An educational toolbox for quantum reservoir computing. arXiv preprint arXiv:2602.03522.

Federal Trade Commission (2026). Consumer sentinel network data book: Social media fraud losses. Technical report, FTC Bureau of Consumer Protection.

Fujii, K. and Nakajima, K. (2017). Harnessing disordered-ensemble quantum dynamics for machine learning. Physical Review Applied, 8(2):024030.

Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., and Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59):1–35.

Huang, J., He, N., Ma, K., Xiao, J., and Wang, H. (2023). A deep dive into NFT rug pulls. In Proceedings of the ACM Internet Measurement Conference (IMC).

Jaeger, H. (2001). The “echo state” approach to analysing and training recurrent neural networks. GMD Technical Report, 148.

Lukoševičius, M. and Jaeger, H. (2009). Reservoir computing approaches to recurrent neural network training. Computer Science Review, 3(3):127–149.

Moreno-Torres, J. G., Raeder, T., Alaiz-Rodríguez, R., Chawla, N. V., and Herrera, F. (2012). A unifying view on dataset shift in classification. Pattern Recognition, 45(1):521–530.

Nakajima, K., Fujii, K., Negoro, M., Mitarai, K., and Kitagawa, M. (2019). Boosting computational power through spatial multiplexing in quantum reservoir computing. Physical Review Applied, 11(3):034021.

Quiñonero-Candela, J., Sugiyama, M., Schwaighofer, A., and Lawrence, N. D., editors (2009). Dataset Shift in Machine Learning. MIT Press, Cambridge, MA.

U.S. Department of Justice (2022). Two defendants charged in non-fungible token (NFT) fraud and money laundering scheme. Press release 22-087, U.S. Attorney’s Office, Southern District of New York.

U.S. Securities and Exchange Commission (2018). SEC charges founders of centra tech inc. with fraudulent initial coin offering. Press release 2018-53, SEC Enforcement Division, Cyber Unit.

Wilson, G. and Cook, D. J. (2020). A survey of unsupervised deep domain adaptation. ACM Transactions on Intelligent Systems and Technology, 11(5):1–46.

Wood, G. (2014). Ethereum: A secure decentralised generalised transaction ledger. Technical report, Ethereum Project. Yellow Paper.

Xia, P., Wang, H., Gao, B., Su, W., Yu, Z., Luo, X., Zhang, C., Xiao, X., and Xu, G. (2021). Trade or trick? Detecting and characterizing scam tokens on Uniswap decentralized exchange. Proceedings of the ACM on Measurement and Analysis of Computing Systems (POMACS), 5(3):1–26.

Xu, J. and Livshits, B. (2019). The anatomy of a cryptocurrency pump-and-dump scheme. In Proceedings of the 28th USENIX Security Symposium, pages 1609–1625.