arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.06180cs.CRcs.LG
收藏

使用蜜罐用户扩展Active Directory图的深度生成模型

Deep Generative Models to Extend Active Directory Graphs with Honeypot Users

Czech Technical University(捷克理工大学)

Ondrej Lukas, Sebastian Garcia

摘要:

Active Directory(AD)是大型组织的关键元素,因为它在管理资源访问方面发挥着核心作用。由于AD被组织中的所有用户使用,因此很难检测到攻击者。我们建议在AD结构中生成并放置假用户(honeyusers)以帮助检测攻击。然而,并不是所有的蜜罐用户都会吸引攻击者。我们的方法生成蜜罐与变分自编码器,丰富了AD结构定位良好的蜜罐。它首先学习AD中原始节点和边的嵌入,然后使用改进的双向DAG-RNN对节点表示的潜在空间的概率分布参数进行编码。最后,它从该分布中采样节点,并使用MLP来决定节点连接的位置。该模型通过生成的AD与原始AD的相似性,新节点的位置,与GraphRNN的相似性进行评估,最后让真正的入侵者攻击生成的AD结构,看看他们是否选择了蜜用户。结果表明,我们的机器学习模型是足够好的,以产生放置良好的蜜罐为现有的AD结构,使入侵者被引诱到他们。

英文摘要:

Active Directory (AD) is a crucial element of large organizations, given its central role in managing access to resources. Since AD is used by all users in the organization, it is hard to detect attackers. We propose to generate and place fake users (honeyusers) in AD structures to help detect attacks. However, not any honeyuser will attract attackers. Our method generates honeyusers with a Variational Autoencoder that enriches the AD structure with well-positioned honeyusers. It first learns the embeddings of the original nodes and edges in the AD, then it uses a modified Bidirectional DAG-RNN to encode the parameters of the probability distribution of the latent space of node representations. Finally, it samples nodes from this distribution and uses an MLP to decide where the nodes are connected. The model was evaluated by the similarity of the generated AD with the original, by the positions of the new nodes, by the similarity with GraphRNN and finally by making real intruders attack the generated AD structure to see if they select the honeyusers. Results show that our machine learning model is good enough to generate well-placed honeyusers for existing AD structures so that intruders are lured into them.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑