东南大学学报(英文版)
東南大學學報(英文版)
동남대학학보(영문판)
JOURNAL OF SOUTHEAST UNIVERSITY
2010年
1期
43-47
,共5页
曹玖新%王田峰%时莉莉%毛波
曹玖新%王田峰%時莉莉%毛波
조구신%왕전봉%시리리%모파
钓鱼检测%图像相似度%特征关系图%内部EMD%外部EMD
釣魚檢測%圖像相似度%特徵關繫圖%內部EMD%外部EMD
조어검측%도상상사도%특정관계도%내부EMD%외부EMD
phishing detection%image similarity%attributed relational graph%inner EMD%outer EMD
提出了一个网络钓鱼防范系统.该系统由客户端过滤插件、后台分析中心和受保护网站3个逻辑组件构成.设计了一个基于图像的网页相似度检测算法,该算法首先将被检测网页转换为图像格式,然后采用迭代分割和收缩算法将原始图像划分为一组子图像集合,在计算子图像颜色直方图、灰度直方图以及大小参数的基础上,构建被检测网页的特征关系图(ARG),计算ARG之间的内部EMD距离,并通过计算2个网页ARG之间的外部EMD距离来标示网页之间的相似度,最终通过对不同网页之间相似度的分析检测出钓鱼网站.实验结果显示所提出的体系结构与算法具有良好的鲁棒性和可扩展性,可对钓鱼网页进行更加有效的检测.
提齣瞭一箇網絡釣魚防範繫統.該繫統由客戶耑過濾插件、後檯分析中心和受保護網站3箇邏輯組件構成.設計瞭一箇基于圖像的網頁相似度檢測算法,該算法首先將被檢測網頁轉換為圖像格式,然後採用迭代分割和收縮算法將原始圖像劃分為一組子圖像集閤,在計算子圖像顏色直方圖、灰度直方圖以及大小參數的基礎上,構建被檢測網頁的特徵關繫圖(ARG),計算ARG之間的內部EMD距離,併通過計算2箇網頁ARG之間的外部EMD距離來標示網頁之間的相似度,最終通過對不同網頁之間相似度的分析檢測齣釣魚網站.實驗結果顯示所提齣的體繫結構與算法具有良好的魯棒性和可擴展性,可對釣魚網頁進行更加有效的檢測.
제출료일개망락조어방범계통.해계통유객호단과려삽건、후태분석중심화수보호망참3개라집조건구성.설계료일개기우도상적망혈상사도검측산법,해산법수선장피검측망혈전환위도상격식,연후채용질대분할화수축산법장원시도상화분위일조자도상집합,재계산자도상안색직방도、회도직방도이급대소삼수적기출상,구건피검측망혈적특정관계도(ARG),계산ARG지간적내부EMD거리,병통과계산2개망혈ARG지간적외부EMD거리래표시망혈지간적상사도,최종통과대불동망혈지간상사도적분석검측출조어망참.실험결과현시소제출적체계결구여산법구유량호적로봉성화가확전성,가대조어망혈진행경가유효적검측.
A phishing detection system,which comprises clientside filtering plug-in,analysis center and protected sites, is proposed. An image-based similarity detection algorithm is conceived to calculate the similarity of two web pages.The web pages are first converted into images,and then divided into subimages with iterated dividing and shrinking.After that, the attributes of sub-images including color histograms, gray histograms and size parameters are computed to construct the attributed relational graph(ARG)of each page.In order to match two ARGs,the inner earth mover's distances(EMD)between every two nodes coming from each ARG respectively are first computed,and then the similarity of web pages by the outer EMD between two ARGs is worked out to detect phishing web pages. The experimental results show that the proposed architecture and algorithm has good robustness along with scalability,and can effectively detect phishing.