网络出版日期: 2025-01-25
基金资助
国家重点研发计划 (2021QY0700);国家自然科学基金(U21B2003,62072250)
版权
A fast low-dimensional method for detecting DNS-over-HTTPS tunnel traffic
Online published: 2025-01-25
Supported by
National Key R&D Program of China (Grants No. 2021QY0700) and the National Natural Science Foundation of China (Grants No. U21B2003,62072250)
Copyright
安全DNS协议DNS-over-HTTPS(DoH)的标准化和部署应用,使DoH隧道成为一种新的隐蔽性网络威胁并受到广泛关注。在云网络环境中对大规模DoH业务流量中潜在的隧道流量进行甄别,需要同时兼顾计算效率和准确率。针对当前基于机器学习的DoH隧道检测算法特征效率低、计算复杂度高的问题,设计了一组数据包块长度特征并提出了一种基于最大相关最小冗余(max-Relevance and Min-Re-dundancy,mRMR)特征筛选算法和随机森林算法的低维快速DoH隧道检测方法,该方法通过特征筛选选取对DoH隧道检测任务贡献大的特征,并使用随机森林分类器进行DoH隧道检测任务。实验结果表明,该方法在仅使用10维特征的情况下,达到了与使用24~34维特征的其他算法相当的准确率,可有效降低部署应用的计算复杂度,更好地适应大规模DoH业务流量分析的应用场景。
关键词: DNS-over-HTTPS; 隧道流量; mRMR算法; 随机森林
王涛 , 翟江涛 , 王子豪 , 张凯杰 , 刘光杰 . 低维快速DNS-over-HTTPS隧道流量检测方法[J]. 网络空间安全科学学报, 2024 , 2(6) : 123 -130 . DOI: 10.20172/j.issn.2097-3136.240609
The standardization and deployment applications of the secure DNS protocol DNS-over-HTTPS (DoH) have brought DoH tunnels to the forefront as a new insidious network threat. Screening potential tunneling traffic among the large-scale DoH service traffic in the cloud network environments requires both computational efficiency and accuracy. Aiming at the low feature efficiency and high computational complexity of the current machine learning-based DoH tunnel detection algorithms, a set of packet block length features was designed and a low-dimensional fast DoH tunnel detection method was proposed based on the max-Relevance and Min-Re-dundancy(mRMR)feature screening algorithm and the random forest algorithm. The features greatly contributing to the DoH tunnel detection task were selected through feature screening and a random forest classifier was used in the DoH tunnel detection task in the proposed method. Experimental results showed that this method achieved a comparable accuracy to other algorithms with using 24 to 34 features, even with using only 10 features. This could effectively reduce the computational complexity of the deployed applications and better adapt to the application scenarios of the large-scale DoH service traffic analysis.
Key words: DNS-over-HTTPS; tunnel traffic; mRMR algorithm; random forest
表 1 本文算法使用特征Table 1 Features used in the algorithm of this paper |
| 特征 | |
| src2dst_mean_length | src2dst_stddev_length |
| dst2src_mean_length | dst2src_stddev_length |
| bidirectional_mean_length | bidirectional_stddev_length |
| src2dst_mean_time | src2dst_stddev_time |
| dst2src_mean_time | dst2src_stddev_time |
| bidirectional_mean_time | bidirectional_stddev_time |
| src2dst_block_mean_length | src2dst_block_stddev_length |
| dst2src_block_mean_length | dst2src_block_stddev_length |
表 2 使用不同维度的特征子集对应的准确率Table 2 Accuracy corresponding to using subsets of features of different dimensions |
| 特征维度 | 准确率 | 误分类样本数 |
| 6 | 470 | |
| 8 | 163 | |
| 10 | 25 | |
| 12 | 20 | |
| 14 | 24 | |
| 16 | 14 |
表 3 本文最终使用的10维特征Table 3 Final 10-dimensional features used in this paper |
| 特征 | |
| src2dst_stddev_length | dst2src_block_stddev_length |
| src2dst_block_mean_length | dst2src_mean_length |
| dst2src_block_mean_length | dst2src_stddev_length |
| src2dst_block_stddev_length | bidirectional_mean_length |
| src2dst_mean_length | bidirectional_stddev_length |
表 4 随机森林超参数Table 4 Random forest hyperparameters |
| 决策树数量 | 最大深度 | 最大叶子节点数 |
| 200 | 20 | None |
表 6 本文方法的时间开销与内存资源占用Table 6 Time overhead and resource consumption of the methods in this paper |
| 数据包数量 | 内存开销/kB | 计算特征用时/ms |
| 3.5 | 0.098 |
| 1 |
李超群,唐纯莹,韩言妮. DNS公共解析服务可用性研究[C]//中国指挥与控制学会. 第十届中国指挥控制大会论文集(下册). 北京:兵器工业出社,2022:7.
LI C Q, TANG C Y, HAN Y N. Research on the availability of DNS public resolution services[C]//China Command and Control Society. Proceedings of the 10th China Command and Control Conference (Volume 2). Beijing: Ordnance Industry Press, 2022:7.
|
| 2 |
张曼,姚健康,李洪涛,等. DNS信道传输加密技术:现状、趋势和挑战[J]. 软件学报,2024,35(1):309-332.
ZHANG M, YAO J K, LI H T, et al. DNS channel transmission encryption technology: Status, trends, and challenges [J]. Journal of Software,2024,35(1):309-332.
|
| 3 |
丁峤, 刘俊延, 刘林云, 等. DNS隧道流量检测特征分析研究[J]. 无线电工程, 2022, 52 (4): 671- 677.
DING Q, LIU J Y, LIU L Y, et al. Research on feature analysis of DNS tunnel traffic detection[J]. Radio Engineering, 2022, 52 (4): 671- 677.
|
| 4 |
DNS Queries over HTTPS (DoH) [S]. RFC8484 IETF,2018.
|
| 5 |
MONTAZERISHATOORI M,DAVIDSON L,KAUR G,et al. Detection of DOH tunnels using time-series classification of encrypted traffic[C]//2020 IEEE Intl Conf on Dependable,Autonomic and Secure Computing,Intl Conf on Pervasive Intelligence and Computing,Intl Conf on Cloud and Big Data Computing,Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech). IEEE,2020:63-70.
|
| 6 |
CIMPANU C. First-ever malware strain spotted abusing new DoH (DNS over HTTPS) protocoll[EB/OL]. (2019-7-3)[2003-12-4]. https: //www.zdnet.com/article/first- ever-malware-strain-spotted-abusing-new-doh-dns-over-https- protocol/.
|
| 7 |
CIMPANN C. Iranian hacker group becomes first known APT to weaponize DNS-over-HTTPS (DoH)[EB/OL]. ( 2020-8-4)[2023-12-4]. https://www.zdnet.com/article/irnanZDNet,2020.
|
| 8 |
CHHABRA R, MURLEY P, KUMAR D, et al. Measuring DNS-over-HTTPS performance around the world[C]//Proceedings of the 21st ACM Internet Measurement Conference. 2021: 351-365.
|
| 9 |
HYNEK K, VEKSHIN D, LUXEEMBURK J, et al. Summary of DNS over HTTPS abuse[J]. IEEE Access, 2022, 10: 54668-54680.
|
| 10 |
BANADAKI Y M, ROBERT S. Detecting malicious DNS over https traffic in domain name system using machine learning classifiers[J]. Journal of Computer Sciences and Applications, 2020, 8 (2): 46- 55.
|
| 11 |
KWAN C,JANISZEWSKI P,QIU S,et al. Exploring simple detection techniques for DNS-over-HTTPS tunnels[C]//Proceedings of the ACM SIGCOMM 2021 Workshop on Free and Open Communications on the Internet. 2021:37-42.
|
| 12 |
DU X,LIU D,DING S,et al. Design of an autoencoder-based anomaly detection for the DoH traffic system[C]//2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE,2022:763-768.
|
| 13 |
NGUYEN A T,PARK M. Detection of DoH Tunneling using semi-supervised learning method[C]//2022 International Conference on Information Networking (ICOIN). IEEE,2022:450-453.
|
| 14 |
ZHAN M, LI Y, YU G, et al. Detecting DNS over HTTPS based data exfiltration[J]. Computer Networks, 2022, 209, 108919.
|
| 15 |
MITSUHASHI R,JIN Y,IIDA K,et al. Malicious DNS tunnel tool recognition using persistent DoH traffic analysis[J]. IEEE Transactions on Network and Service Management,2022,20(2):2086-2095.
|
| 16 |
VEKSHIN D,HYNEK K,CEJKA T. DOH insight:detecting DNS over https by machine learning[C]//Proceedings of the 15th International Conference on Availability,Reliability and Security. 2020:1-8.
|
| 17 |
ALENEZI R,LUDWIG S A. Classifying DNS tunneling tools for malicious DoH traffic[C]//2021 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE,2021:1-9.
|
| 18 |
JHA H, PATEL I, LI G, et al. Detection of tunneling in DNS over HTTPS[C]//2021 7th International Conference on Signal Processing and Communication (ICSC). IEEE, 2021: 42-47.
|
| 19 |
LI B, HE S, PENG H, et al. Detecting DoH tunnels with privacy protection using federated learning[C]//International Conference on Network Communication and Information Security (ICNCIS 2021). SPIE, 2022, 12175: 133-141.
|
| 20 |
孙林, 徐枫, 李硕, 等. 基于ReliefF和最大相关最小冗余的多标记特征选择[J]. 河南师范大学学报(自然科学版), 2023, 51 (6): 21- 29,175.
SUN L, XU F, LI S, et al. Multi-label feature selection based on reliefF and maximum relevance minimum redundancy[J]. Journal of Henan Normal University (Natural Science Edition), 2023, 51 (6): 21- 29,175.
|
| 21 |
张婧,曹峰,董毓莹,等. 基于互信息和遗传算法的特征选择算法[J]. 山西大学学报(自然科学版),2024,47(1):1-8.
ZHANG J, CAO F, DONG Y Y, et al. Feature selection algorithm based on mutual information and genetic algorithm[J]. Journal of Shanxi University (Natural Science Edition), 2024, 47(1): 1-8.
|
| 22 |
吕广旭, 卢加奇, 魏先燕, 等. 基于随机森林-聚类混合方法的多分类入侵检测研究[J]. 现代信息科技, 2022, 6 (16): 165- 167.
LÜ G X, LU J Q, WEI X Y, et al. Research on multi-class intrusion detection based on random forest-clustering hybrid method[J]. Modern Information Technology, 2022, 6 (16): 165- 167.
|
| 23 |
杨剑锋, 乔佩蕊, 李永梅, 等. 机器学习分类问题及算法研究综述[J]. 统计与决策, 2019, 35 (6): 36- 40.
YANG J Q, QIAO P R, LI Y M, et al. A review of machine learning classification problems and algorithms[J]. Statistics and Decision, 2019, 35 (6): 36- 40.
|
| 24 |
章文俊, 韩晓龙. 基于交叉验证网格寻优随机森林的黑产用户识别方法[J]. 科技视界, 2019, (28): 1- 3,7.
ZHANG W J, HAN X L. Black industry user identification method based on cross-validation grid optimization random forest[J]. Science & Technology Horizon, 2019, (28): 1- 3,7.
|
/
| 〈 |
|
〉 |