Computer-implemented method for detecting anomalies in application programming interface calls within network using behavior profiling, involves declining application programming interface calls based on risk score associated with application programming interface calls being equal to threshold
	VIMAL S; SANKHALA R K; MCGUIGAN B M; DHAMA G; WADHWA H
	2023-10-11
专利权人	MASTERCARD INT INC (MSTC-C)
申请日期	2023-10-11
专利号	IN202341068307-A
成果简介	NOVELTY - The method involves extracting subset of API calls associated with each anomalous node of the set of anomalous nodes from short-term API call data (114B) by a server system (102). A reconstruction loss corresponding to each API call of the subset of API calls is generated by the server system via a machine leaning (ML) model (116) based on analyzing the subset of API calls. A risk score for each API call of the subset of API calls is generated by the server system via the ML model based on the corresponding reconstruction loss. API calls are declined by the server system based on the risk score associated with the API calls being equal to an anomaly detection threshold, where the ML model comprises variational Autoencoder (VAE) model trained using deep learning neural networks. USE - Computer-implemented method for detecting anomalies in API calls within a network using behavior profiling. ADVANTAGE - The method enables preventing malicious entities such as hackers, from attacking an API network/infrastructure for malicious gains, thus making case of API calls security imperative effectively. The method allows the API network to be protected from malicious entities. DETAILED DESCRIPTION - INDEPENDENT CLAIMS are also included for: A server system; and A non-transitory computer-readable storage medium comprising a set of instructions for detecting anomalies in API calls within a network using behavior profiling. DESCRIPTION OF DRAWING(S) - The drawing shows a schematic block diagram of a system for detecting anomalies in API calls within a network using behavior profiling. 104Node 106Data source 108Database 110Network 114API call dataset 114BShort-term API call data 116ML model
IPC 分类号	G06F-021/56 ; G06F-009/54 ; G06N-020/00 ; G06N-003/04 ; H04M-007/00
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/20024
专题	中国科学院新疆生态与地理研究所
作者单位	MASTERCARD INT INC (MSTC-C)
推荐引用方式 GB/T 7714	VIMAL S,SANKHALA R K,MCGUIGAN B M,et al. Computer-implemented method for detecting anomalies in application programming interface calls within network using behavior profiling, involves declining application programming interface calls based on risk score associated with application programming interface calls being equal to threshold. IN202341068307-A[P]. 2023.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。