基于WriteUp图文内容分析的网安竞赛作弊检测技术

张方娇; 刘心宇; 刘宝旭; 赵建军; 刘奇旭; 崔翔

引用本文：

张方娇,刘心宇,刘宝旭,赵建军,刘奇旭,崔翔.基于WriteUp图文内容分析的网安竞赛作弊检测技术[J].信息安全学报,已采用 [点击复制]
ZHANG Fangjiao,LIU Xinyu,LIU Baoxu,ZHAO Jianjun,LIU Qixu,CUI Xiang.Cheating Behavior Detection Based on Image and Text Similarity of WriteUp[J].Journal of Cyber Security,Accept [点击复制]

本文已被：浏览 1684次下载 302次
基于WriteUp图文内容分析的网安竞赛作弊检测技术
张方娇¹, 刘心宇¹, 刘宝旭¹, 赵建军¹, 刘奇旭¹, 崔翔²
0 字体:加大+\|默认\|缩小-
(1.中国科学院信息工程研究所;2.广州大学网络空间先进技术研究院)

摘要:

网络空间安全问题层出不穷，网络空间安全人才（以下简称网安人才）缺口大，如何确保网安人才评估的公平公正并选拔出符合要求的网安人才成为当务之急。针对当前网络安全竞赛（以下简称网安竞赛）中普遍存在的作弊现象及大量WriteUp（赛题的解题过程文档）审核难的问题，本文提出了一种基于WriteUp图文内容分析的作弊检测技术，从图像内容相似性和文本内容相似性两个维度检测网安竞赛中可能存在的作弊行为。在图像相似性计算方面，采用基于均值哈希的相似性计算、基于直方图的相似性计算、基于图像长宽比的相似性计算三种算法对图像内容进行相似性对比；在文本相似性计算方面，从词频相似性和词语转移概率相似性两个方面对文本内容进行相似性对比。通过对30份WriteUp的图文内容进行分析，本文提出的作弊检测方法可准确地识别出网安竞赛中存在的作弊行为，验证了检测方法的可行性和有效性。同时，根据Flag（解出赛题即可获得相应的Flag）提交时间可对作弊源头进行追溯。本文提出的作弊检测方法也可适用于其他网安人才评估方法。

关键词: 网安人才评估网安竞赛 WriteUp 作弊检测图像相似性文本相似性

DOI：10.19363/J.cnki.cn10-1380/tn.2024.04.15

投稿时间：2022-01-20修订日期：2022-07-12

基金项目:国家自然科学基金项目(No.61902396)、、中国科学院青年创新促进会(No.2019163)、中国科学院战略性先导科技专项项目(No.XDC02040100)、中国科学院网络测评技术重点实验室和网络安全防护技术北京市重点实验室

Cheating Behavior Detection Based on Image and Text Similarity of WriteUp

ZHANG Fangjiao¹, LIU Xinyu¹, LIU Baoxu¹, ZHAO Jianjun¹, LIU Qixu¹, CUI Xiang²

(1.Institute of Information Engineering,Chinese Academy of Sciences;2.Cyberspace Institute of Advanced Technology, Guangzhou University)

Abstract:

Cybersecurity issues emerge in endlessly and cybersecurity talents’ gap is huge. How to ensure the fairness and justice of cybersecurity talents evaluation and select qualified cybersecurity talents have become a top priority. For the cheating in cybersecurity competitions and the difficulty of many WriteUps checking, this paper proposes a cheating behavior de-tection method. It checks the cheating across two dimensions: image similarity and text similarity. Three algorithms are adopted to compute the image similarity by using histogram, mean hash and length-width ratio. Word frequency similar-ity and word transferring probability similarity are used to compute the text similarity. Through 30 WriteUps with con-tent analysis, the cheating detection method could identify cheating behaviors in competitions, which verifies feasibility and effectiveness of the method. Meanwhile, the cheating source could be traced according to flags’ submission time. The corresponding flags are obtained by solving competition questions. The detection method proposed in this paper can be applied to other cybersecurity talents evaluation.

Key words: cybersecurity talents evaluation cybersecurity competitions WriteUp cheating detection image similarity text similarity