基于HMM的私有協(xié)議自主學(xué)習(xí)方法
發(fā)布時(shí)間:2019-02-24 20:04
【摘要】:針對近年來工控網(wǎng)絡(luò)中私有協(xié)議的廣泛應(yīng)用,給安全研究帶來許多挑戰(zhàn),提出基于隱馬爾可夫模型的私有協(xié)議自主學(xué)習(xí)方法,僅通過流量數(shù)據(jù)得到私有協(xié)議報(bào)文結(jié)構(gòu)的有限狀態(tài)機(jī)模型。并且針對Baum-Welch算法需要先驗(yàn)知識(shí)的缺點(diǎn),基于因果態(tài)分割重建算法的思想,設(shè)計(jì)出求解私有協(xié)議報(bào)文結(jié)構(gòu)ε機(jī)模型的CAPP算法,避免了局部最優(yōu)和由于缺乏先驗(yàn)知識(shí)所產(chǎn)生的參數(shù)選擇問題;通過公有協(xié)議FTP、Modbus TCP以及私有協(xié)議WDB RPC對方法的有效性進(jìn)行了實(shí)驗(yàn)驗(yàn)證。最后討論了下一步的研究方向。
[Abstract]:In view of the wide application of private protocols in industrial control networks in recent years, which brings many challenges to security research, a private protocol autonomous learning method based on hidden Markov model is proposed. The finite state machine model of private protocol packet structure is obtained only by traffic data. Aiming at the shortcoming of Baum-Welch algorithm which needs prior knowledge, based on the idea of causal state partition reconstruction algorithm, a CAPP algorithm is designed to solve the 蔚 machine model of private protocol message structure. The problem of parameter selection caused by local optimization and lack of prior knowledge is avoided. The effectiveness of the method is verified by public protocol FTP,Modbus TCP and private protocol WDB RPC. Finally, the next research direction is discussed.
【作者單位】: 火箭軍工程大學(xué)信息工程系;
【基金】:國家自然科學(xué)基金青年基金資助項(xiàng)目(61403397) 陜西省自然科學(xué)基礎(chǔ)研究計(jì)劃資助項(xiàng)目(2015JM6313)
【分類號(hào)】:TP181
本文編號(hào):2429884
[Abstract]:In view of the wide application of private protocols in industrial control networks in recent years, which brings many challenges to security research, a private protocol autonomous learning method based on hidden Markov model is proposed. The finite state machine model of private protocol packet structure is obtained only by traffic data. Aiming at the shortcoming of Baum-Welch algorithm which needs prior knowledge, based on the idea of causal state partition reconstruction algorithm, a CAPP algorithm is designed to solve the 蔚 machine model of private protocol message structure. The problem of parameter selection caused by local optimization and lack of prior knowledge is avoided. The effectiveness of the method is verified by public protocol FTP,Modbus TCP and private protocol WDB RPC. Finally, the next research direction is discussed.
【作者單位】: 火箭軍工程大學(xué)信息工程系;
【基金】:國家自然科學(xué)基金青年基金資助項(xiàng)目(61403397) 陜西省自然科學(xué)基礎(chǔ)研究計(jì)劃資助項(xiàng)目(2015JM6313)
【分類號(hào)】:TP181
【相似文獻(xiàn)】
相關(guān)期刊論文 前5條
1 楊國亮;王志良;劉冀偉;陳鋒軍;王國江;;一種改進(jìn)的HMM訓(xùn)練算法及其在面部表情識(shí)別中的應(yīng)用[J];計(jì)算機(jī)科學(xué);2006年11期
2 陸汝華;王魯達(dá);;基于狀態(tài)加權(quán)合成的HMM滾動(dòng)軸承故障診斷[J];軸承;2011年10期
3 李士民,郭立,朱嘉;一種基于HMM的多傳感器多目標(biāo)快速跟蹤算法[J];系統(tǒng)工程與電子技術(shù);2002年05期
4 黎昱,黃席樾,周欣;基于免疫聚類與HMM的時(shí)序信息系統(tǒng)決策[J];信息與控制;2003年05期
5 肖佳林;趙聿晴;王英;;基于HMM與SVM的語音活動(dòng)檢測[J];計(jì)算機(jī)工程;2014年01期
相關(guān)碩士學(xué)位論文 前2條
1 曹立立;基于HMM的TE過程在線故障診斷與多步故障預(yù)報(bào)[D];華中科技大學(xué);2015年
2 謝麗君;基于HMM的家庭服務(wù)機(jī)器人情感計(jì)算模型研究[D];華南理工大學(xué);2011年
,本文編號(hào):2429884
本文鏈接:http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2429884.html
最近更新
教材專著