반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

한국반도체디스플레이기술학회 (The Korean Society Of Semiconductor & Display Technology)
권호 표지

CNN 모델을 이용한 사기 스마트 컨트랙트 탐지

Fraudulent Smart Contract Detection Using CNN Models

  • 박다은 (단국대학교 컴퓨터학과) ;
  • 박용범 (단국대학교 소프트웨어학과)
  • Daeun Park (Dankook University Dpt. of Computer Science) ;
  • Young B. Park (Dankook University Dpt. of Software )
  • 투고 : 2023.08.16
  • 심사 : 2023.09.12
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

As the DeFi market continues to expand, fraudulent activities using smart contracts have also increased. HoneyPot and Ponzi schemes are well-known frauds that exploit smart contracts. While several studies have demonstrated the potential to detect smart contracts implementing these scams, there has been a lack of research focusing on simultaneously detecting both types of fraud. This paper addresses this gap by harnessing artificial intelligence to conduct experiments for the detection of both HoneyPot and Ponzi schemes. The study employs the CNN (Convolutional Neural Network) model, commonly used for malware detection. To effectively utilize CNN, the bytecode of smart contracts is transformed into visual representations. The experimental results showcase a recall rate of 0.89 and an F1 score of 0.85, indicating promising detection capabilities.

키워드

과제정보

이 논문은 2023년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 (2021-0-00177, 스마트 컨트랙트의 개발-배포-실행의 전주 기적 취약점 및 신뢰성 오류 개선 기술개발)

참고문헌

  1. Dong-Bin Choi, In-su Jo and Young B. Park. (2021) Comparison of Code Similarity Analysis Performance of funcGNN and Siamese Network, Journal of the Semiconductor & Display Technology, 20(3), 113-116.
  2. F. Zhong, Z. Chen, M. Xu, G. Zhang, D. Yu and X. Cheng, "Malware-on-the-Brain: Illuminating Malware Byte Codes With Images for Malware Classification," in IEEE Transactions on Computers, vol. 72, no. 2, pp. 438-451, 1 Feb. 2023, doi: 10.1109/TC.2022.3160357.
  3. Marastoni, Niccolo, Roberto Giacobazzi, and Mila Dalla Preda. "Data augmentation and transfer learning to classify malware images in a deep learning context." Journal of Computer Virology and Hacking Techniques 17 (2021): 279-297. https://doi.org/10.1007/s11416-021-00381-3
  4. Daoudi, Nadia, et al. "Dexray: a simple, yet effective deep learning approach to android malware detection based on image representation of bytecode." Deployable Machine Learning for Security Defense: Second International Workshop, MLHat 2021, Virtual Event, August 15, 2021, Proceedings 2. Springer International Publishing, 2021.
  5. Nataraj, Lakshmanan, et al. "Malware images: visualization and automatic classification." Proceedings of the 8th international symposium on visualization for cyber security. 2011.
  6. Pinhero, Anson, et al. "Malware detection employed by visualization and deep neural network." Computers & Security 105 (2021): 102247.
  7. "Verified Contracts", Etherscan, accessed Aug 07, 2023, https://etherscan.io/contractsVerified
  8. C. F. Torres, M. Steichen, and R. State, "The art of the SCAM: Demystifying honeypots in ethereum smart contracts," in Proc. 28 USENIX Security Symp., 2019, pp. 1591-1607.
  9. M. Bartoletti et al., "Dissecting ponzi schemes on ethereum: identification, analysis, and impact," arXiv preprint arXiv:1703.03779, 2017.
  10. Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556, 2014.
  11. He, Kaiming, et al. "Identity mappings in deep residual networks." Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV 14. Springer International Publishing, 2016.