基于靜態(tài)行為軌跡的異常特征檢測技術
發(fā)布時間:2018-12-07 16:38
【摘要】:針對現有程序靜態(tài)異常特征檢測中存在的對未知變種識別率低的問題,提出一種基于靜態(tài)行為軌跡的特征提取與檢測方法。特征建模階段采用變長n-gram算法對樣本的函數調用序列進行特征建模,并從中提取異常特征;檢測階段通過對函數調用序列的分片所生成的軌跡段與特征庫中的序列段進行匹配,并將可信度加入判決值的計算中,與判決閾值作比較,以克服靜態(tài)基于字節(jié)序列的特征碼檢測誤報率較高的缺陷。實驗表明,基于靜態(tài)行為軌跡的異常特征檢測技術具有較高的準確率和較低的誤報率。
[Abstract]:In order to solve the problem of low recognition rate of unknown varieties in static anomaly feature detection of existing programs, a feature extraction and detection method based on static behavior trajectory is proposed. In the stage of feature modeling, the variable length n-gram algorithm is used to model the feature of the function calling sequence of the sample, and the abnormal feature is extracted from it. In the detection stage, the trace segment generated by the fragment of the function calling sequence is matched with the sequence segment in the signature library, and the credibility is added to the calculation of the decision value, and compared with the decision threshold. In order to overcome the high false alarm rate of static signature detection based on byte sequence. The experimental results show that the anomaly detection technique based on static behavior trajectory has higher accuracy and lower false alarm rate.
【作者單位】: 數學工程與先進計算國家重點實驗室;
【基金】:國家自然科學基金資助項目(61472447)
【分類號】:TP309
本文編號:2367474
[Abstract]:In order to solve the problem of low recognition rate of unknown varieties in static anomaly feature detection of existing programs, a feature extraction and detection method based on static behavior trajectory is proposed. In the stage of feature modeling, the variable length n-gram algorithm is used to model the feature of the function calling sequence of the sample, and the abnormal feature is extracted from it. In the detection stage, the trace segment generated by the fragment of the function calling sequence is matched with the sequence segment in the signature library, and the credibility is added to the calculation of the decision value, and compared with the decision threshold. In order to overcome the high false alarm rate of static signature detection based on byte sequence. The experimental results show that the anomaly detection technique based on static behavior trajectory has higher accuracy and lower false alarm rate.
【作者單位】: 數學工程與先進計算國家重點實驗室;
【基金】:國家自然科學基金資助項目(61472447)
【分類號】:TP309
【相似文獻】
相關期刊論文 前2條
1 陶闖;;LBS市場發(fā)展趨勢和挑戰(zhàn)[J];衛(wèi)星與網絡;2012年10期
2 ;[J];;年期
相關重要報紙文章 前2條
1 趙朕(中國解放區(qū)文學研究會副會長);單純的綠色 復雜的折光[N];中國紀檢監(jiān)察報;2001年
2 任正虎;抓好團以上黨委書記隊伍建設[N];解放軍報;2003年
相關碩士學位論文 前5條
1 馮琳耀;基于室內傳感網數據的行為軌跡幾何代數建模與特征分析方法[D];南京師范大學;2015年
2 趙方旭;不同水力條件下魚類個體行為軌跡特性研究[D];廣西大學;2016年
3 周永;基于簽到數據的用戶行為軌跡相似度分析[D];西華大學;2016年
4 王彬;用戶行為軌跡聚類及其應用研究[D];西華大學;2016年
5 韓金娥;基于化簡行為軌跡的軟件可信性評價模型[D];河北大學;2011年
,本文編號:2367474
本文鏈接:http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2367474.html