暂无图片
暂无图片
暂无图片
暂无图片
暂无图片
大型指纹库场景中加密视频识别方法-吴桦,于振华,程光,胡晓艳.pdf
268
23页
2次
2022-05-26
免费下载
软件学报 ISSN 1000-9825, CODEN RUXUEW
Journal of Software, [doi: 10.13328/j.cnki.jos.006025]
©国科学院软件研究所版权所.
大型纹库场景中加密视
识别方法
1,2,3
,
1
,
1,2,3
,
1,2,3
1
(南大 络空间安全学,江苏 211189)
2
(南大 育部计算机网络和息集成重点实验室,
江苏
3
(南大 苏省计算机网络重实验, 南京
211189)
通讯作者: , E-mail: hwu@seu.edu.cn
:
加密视频识别是网络安全和网络管理领域亟待解决的问题
指纹库中的视频指纹进行匹配,
从而识别出加密传输的视频
专门针对待匹配数据源的研,也缺少在
大型视频指纹库里
.,
使
Unit,ADU)密文长度相对明文长度发生漂移的原因,
首次将
的拟合特征,提出了一种对加密 ADU
指纹精准复原方法
频模拟构建了二十万级的大型指纹库.
从理论上推导并计算出
中视频识别准确率、查准率、查全率达到 100%,
假阳率
果一致.HHTF 方法的应用使得在
大规模视频指纹库场景中识别加密传输的视频成为可能
用价值.
关键词: 加密视频识别; 应用数据单元; 传输指纹;
大型
图法类号: TP393
: , , , .
http://www.jos.org.cn/1000-9825/6025.htm
英文引用格式: Wu H, Yu ZH, Cheng G, Hu XY.
Encrypted
Bao/Journal of Software, (in Chinese).
http://www.jos.org.cn/1000
Encrypted Video Recognition in Large-scale
F
WU Hua
1,2,3
, YU Zhen-Hua
1
, CHENG Guang
1,2,3
,
HU
1
(
School of Cyber Science and Engineering, Southeast University, Nanjing 211189
2
(Key Laboratory of Computer Network and Information Integration of Ministry of
211189, China)
3
(
Key Laboratory of Computer Network Technology of Jiangsu Province,
Abstract:
Encrypted video identification is an urgent problem in the field of network security and network management. The existing
methods are to match the video transmission fingerprint of encrypted video with the video fingerprint in the video fi
The existing research mainly focuses on the study of matching recognition algorithm, but there is no particular research on m
sources, nor the analysis of precision and false positive
rate in large
基金: 国家发计课题(
2017YFB0801703
家自然科学基金项(61602114);
赛尔网络下一代互联网技术创新项目
Foundation item: National Key R&D
Program of China (2017YFB0801703
Mobile Research Fund Project (MCM20180506),
the National Natural Science Foundation of China (61602114)
Project(NGIICS20190101,NGII20170406).
收稿时间:
2019-10-07; 改时: 2020-01-06; 采用时间:
E-mail: jos@iscas.ac.cn
http://www.jos.org.cn
Tel: +86-10-62562563
识别方法
江苏
211189)
211189)
加密视频识别是网络安全和网络管理领域亟待解决的问题
,已有的方法是将视频的加密传输指纹与视
从而识别出加密传输的视频
.现有研究主要集中在匹配识别算法的研究,但是没有
大型视频指纹库里
对这些算法的查准率和假阳率指标分析,此造成现有
使
Application Data
首次将
HTTP 头部特征和 TLS 片段特征作为 ADU 长度复原
指纹精准复原方法
HHTF,并将其应用于加密视频识别.基于真实 Facebook
从理论上推导并计算出
,只需要已有方法十分之一的 ADU 数目,在该指纹库
假阳率
达到 0.在模拟大型视频指纹库中的实验结果与理论推导结
大规模视频指纹库场景中识别加密传输的视频成为可能
,具有很强的实用性和应
大型
视频指纹库 ;安全传输层协议
. .
Encrypted
Video Recognition in Large Fingerprint Database. Ruan Jian Xue
http://www.jos.org.cn/1000
-9825/6025.htm
F
ingerprint Database
HU
Xiao-Yan
1,2,3
School of Cyber Science and Engineering, Southeast University, Nanjing 211189
, China)
(Key Laboratory of Computer Network and Information Integration of Ministry of
Education of China, Southeast University,Nanjing
Key Laboratory of Computer Network Technology of Jiangsu Province,
Southeast University, Nanjing 211189, China)
Encrypted video identification is an urgent problem in the field of network security and network management. The existing
methods are to match the video transmission fingerprint of encrypted video with the video fingerprint in the video fi
ngerprint database.
The existing research mainly focuses on the study of matching recognition algorithm, but there is no particular research on m
atching data
rate in large
-scale video fingerprint library. The resulting practicality of existing
2017YFB0801703
,2018YFB1800602); 教育-动科(MCM20180506);
赛尔网络下一代互联网技术创新项目
(NGIICS20190101,NGII20170406)
Program of China (2017YFB0801703
, 2018YFB1800602), Ministry of Education-China
the National Natural Science Foundation of China (61602114)
,the CERNET Innovation
2020-02-28; jos 在线出版时间: 2021-05-20
2
Journal of Software 软件学报
methods cannot be guaranteed. In order to address this problem, this paper firstly analyses the reason why the length of the ciphertext of
the application data unit (ADU) encrypted by TLS drifts relative to the length of the plaintext.
For the first time, HTTP head feature and
TLS fragment features are used as fitting features for ADU length restoration, then this paper proposes an accurate fingerprint restoration
method HHTF for the encrypted ADU, and applies HHTF to the encrypted video recognition. A large fingerprint database of 200,000
videos was built based on the simulation of real Facebook videos. Theoretical derivation and calculation demonstrate that the accuracy,
precision and recall rate can reach 100%, and the false positive rate is 0 requiring only one-tenth the number of ADUs of the existing
method. The experimental results in simulating large-scale video fingerprint database are consistent with the theoretical calculations. The
application of the HHTF method makes it possible to recognize encrypted transmitted video in large-scale video fingerprint library scenes,
which is of great practicality and application value.
Key words: encrypted video identificationapplication data unit transmission fingerprintlarge-scale video fingerprint database
Transport Layer Security Protocol
联网计功不上,和安是互考虑,
TLSTransport Layer Security,TLS实现据的到端密传输是通用加密输方.由于据重
程度一样,有些只对登录据加,有些所有据都传输,件成的下和人
,,.,
密流比重增加给网安全网络理带来极的挑.
如何加密数据中抽出网安全护和网络理需的信已经成为家安部门络管理中
决的,要保通网隐私,及时因特传递危害和社安全,这需能够
在不密信的前提下准识特定被加密信.
目前加密量的分析要分两大应用类型别和容识.对加流量的应类型别开展的
,范围广,
[1]
,
[2-4]
,识别
[5-7]
,密视播放式的
[8]
, 密视务平识别
[9,10]
, 加密频服质量
[10-14]
.这类究都
不涉到用信息的具内容.
络管较大,
网站访问行识别. 2018 年思公司全球互联流量究报
[15]
,互联网全流量超过 70%频流
,计到 2022 ,频流的比将增长到 80%,并且世界 TOP 频服务商已经用了加密频传
.,,广,待解.
别同的需括加访问
[16-18]
.这两的流互联的绝,
加密输的,对这类应用内的识成为网络全管的挑.
本文研究绕加密视内容别展.
频的容标,对视画面容进,以下为加视频.于应信息加密法直
分析,道是分析常见,频识基本网络输层
议头信息提取出应数据元(Application Data Unit,ADU的特.ADU 应用信息传输的数
[19]
, HTTP 传输议中 HTTP 的资源就一个 ADU. ADU 数据长度传输序构成了
应用信息指纹,者有可能这些 ADU 特征别出用层信息.
[20-26]
.研究
,将采的加输数视频库进配以热点.识别的输
——
配的数据中的,构建,及由的构来的偏差
进行入研.库规大后,不确会极响着些识法的.第二题是有研
结果, ,少有,别是
; ,
些算,大型
.,使,,
of 23
免费下载
【版权声明】本文为墨天轮用户原创内容,转载时必须标注文档的来源(墨天轮),文档链接,文档作者等基本信息,否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容,欢迎发送邮件至:contact@modb.pro进行举报,并提供相关证据,一经查实,墨天轮将立刻删除相关内容。

评论

关注
最新上传
暂无内容,敬请期待...
下载排行榜
Top250 周榜 月榜