FUR-API: Dataset and Baselines Toward Realistic API Anomaly Detection

Yijun Liu, Honglan Yu, Feifei Dai, Xiaoyan Gu, Chenxu Cui, Bo Li, Weiping Wang

Abstract: The Application Program Interface (API) security is crucial for data security as it ensures the safety and authority of data exchange between different applications. However, the absence of high-quality datasets significantly impedes the development of API anomaly detection. This paper presents a benchmark dataset and baselines for realistic API anomaly detection involving few-shot and unknown-risk scenarios. The dataset is synthesized using an Iterative data Generation approach with Dual-channel Filtering (IGDF). By leveraging large language models and dual-channel filtering models, we can iteratively generate and filter data, yielding a high-quality dataset. Moreover, we have developed baselines and conducted extensive experiments on the proposed dataset. The results indicate that few-shot and unknown-risk API anomaly detection remains a challenging task and still requires further research. All details and resources are released at https://github.com/yijunL/FUR-API.