ASAhyun Song

Ahyun Song

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ahyun Song has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Deep Learning-based Anomaly Detection in the USDT Stablecoin

    by Ahyun Song, Euiseong Seo, Heeyoul Kim

    본 논문은 대표적인 스테이블코인인 USDT의 온체인 거래 데이터를 분석하여 딥러닝 모델을 활용해 이상 행위를 탐지하는 방법론을 제안한다. 이더리움 블록체인 상의 ERC-20 기반 USDT 거래 데이터를 수집하고 분석해, 이를 시간 단위로 집계하여 총 6개의 피처(전송량, 거래 수, 송신자 수, 수신자 수, 발행량, 소각량)를 추출하였다. 이후 Anomaly VAE-Transformer 모델을 구성하고, 비지도 학습 방식으로 정상 패턴을 학습한 뒤 재구성 오차 기반 이상 스코어를 계산하였다. 도출된 스코어를 통해 탐지된 이상 구간에 대한 분석을 수행했고, 급격한 발행·소각, 거래 집중 등 다양한 이상 패턴을 효과적으로 탐지하였음을 보였다. 본 논문은 스테이블코인의 거래에 대해 이상 거래를 조기에 탐지할 수 있는 기반을 제공하며, 향후 디파이 생태계의 안정성과 보안성을 강화하는 데 기여할 것으로 기대된다.

  • Open Access

    Anomaly VAE-Transformer: A Deep Learning Approach for Anomaly Detection in Decentralized Finance

    by Ahyun Song, Euiseong Seo, Heeyoul Kim

    DeFi, a decentralized financial service based on blockchain, not only provides innovative financial services, but also poses various risks, such as the Terra Luna crash. Therefore, anomaly detection in DeFi is necessary to ensure the safety and reliability of the DeFi ecosystem. However, this is very difficult because of the complex protocol, interaction among smart contracts, and high market volatility. In this study, we propose a novel method to effectively detect anomalies in DeFi. To the best of our knowledge, this is the first study that utilizes deep learning to detect anomalies in DeFi. We propose a deep learning model, anomaly VAE-Transformer, which combines the variational autoencoder to extract local information in the short term, and the transformer, to identify dependencies between data in the long term. Based on a deep understanding of DeFi protocols, the proposed model collects and analyzes various on-chain data of Olympus DAO, a representative DeFi protocol, for extracting features suitable for anomaly detection. Then, we demonstrate the superiority of the proposed model by analyzing four anomaly cases detected successfully by the proposed model in Olympus DAO. A malicious attack attempt and structural changes in DeFi protocols can be identified quickly using the proposed method; this is expected to help protect the assets of DeFi users and improve the safety, reliability, and transparency of the DeFi market. The dataset and codes are available at https://github.com/fialle/Anomaly-VAE-Transformer.


  • Territoriality of Locally Unwanted Facilities: The Case of Boramae Waste Transfer Station

    by Ahyun Song, Kyusang Kwon

    We examine the territoriality of locally unwanted facilities using a case study of Boramae waste transfer station (BWTS). Previous studies on locally unwanted facilities have paid less attention to the changes in conflicts over location of facilities as they are often trapped into a methodological territorialism that perceives a territory as being self-closed and fixed. Through considering territory as the effect of network proposed by Joe Painter, we argue that conflicts over the location and operation of locally unwanted facilities should be understood as a process of the territorialization, and reterritorialization through constant changes in the network among various actors under the specific geographical and historical conditions. The territory of BWTS was produced by engagement between Gwanak-gu and Dongjak-gu government in accordance with changes in the waste management strategies of the central government and Seoul metropolitan government. However, faced with complaints from nearby residents, Dongjak-gu made connections to other actors, leading to subsequent reterritorialization. This study can contribute to the debate on the geography of waste and locally unwanted facilities through analyzing the territoriality of BWTS in the perspective of territory as the effect of network.