白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Context informed abnormal endpoint behavior detection

專利號
US11888881B2
公開日期
2024-01-30
申請人
Palo Alto Networks, Inc.(US CA Santa Clara)
發(fā)明人
Shai Meir; Dany Cohen; Arkady Miasnikov; Ohad Ohayon
IPC分類
H04L9/40; G06N20/00
技術領域
causality,event,endpoint,adaptive,profile,malicious,security,file,normal,events
地域: CA CA Santa Clara

摘要

Adaptive normal profiles are generated at a hierarchical scope corresponding to a set of endpoints and a process. Abnormal endpoint activity is detected by verifying whether event data tracking activity on the set of endpoints conforms to the adaptive normal profiles. False positives are reduced by verifying alarms correspond to normal endpoint activity. Abnormal event data is forwarded to a causality chain identifier that identifies abnormal chains of processes for the abnormal endpoint activity. A trained threat detection model receives abnormal causality chains from the causality chain identifier and indicates a likelihood of corresponding to a malicious attack that indicates abnormal endpoint behavior.

說明書

At block 601, the security monitor retrieves those of the adaptive normal profiles of the process with a scope corresponding to an endpoint or multiple endpoints on which the process is running. The security monitor queries a profile database with a process identifier and scoping parameters that includes the endpoint(s). The profile database can return multiple adaptive profiles having multiple hierarchical scopes corresponding to the endpoints running the process. For example, endpoints in distinct business units both running the process can correspond to distinct adaptive normal profiles having hierarchical scopes for each business unit. The profile database can be a remote database or a database running on local memory (e.g., when the security monitor is running on a monitoring agent at an endpoint). The profile database can be configured to retrieve all adaptive normal profiles corresponding to a set of endpoints efficiently, without backtracking to previously retrieved adaptive normal profiles.

At block 602, example operations for monitoring a process proceed as indicated by blocks 603, 607, 609, 611, and 613. The flowchart in FIG. 6 depicts the operations in blocks 603, 607, 609, 611, and 613 as being performed for a single process in each iteration, however these operations can occur for multiple processes simultaneously depending upon implementation (e.g., a multi-threaded processor, prioritization of processes, etc.). Components performing each block can receive activity corresponding to multiple processes running on multiple endpoints independently of other components also evaluating process activity.

權利要求

1
微信群二維碼
意見反饋