Precise Extraction of Malicious Behaviors

摘要: In recent years, the damage cost caused by malwares is huge. Thus, malware detection a big challenge. The task of specifying takes huge amount time and engineering effort since it currently requires manual study malicious code. in order to avoid tedious analysis codes, this has be automatized. To aim, we propose work represent behaviors using extended API call graphs, where nodes correspond function calls, edges specify execution between functions, edge labels indicate dependence relation functions parameters. We define new static techniques that allow extract such graphs from programs, show how automatically extract, set benign an graph represents behaviors. Finally, can used for detection. implemented our obtained encouraging results: 95.66% rate with 0% false alarms.