Phát triển Framework ứng dụng AI hỗ trợ tự động khai thác lỗ hổng bảo mật

Tóm tắt—Hiện nay, nhiệm vụ đánh giá an toàn thông tin cho các hệ thống thông tin có ý nghĩa quan trọng trong đảm bảo an toàn thông tin. Đánh giá/khai thác lỗ hổng bảo mật cần được thực hiện thường xuyên và ở nhiều cấp độ khác nhau đối với các hệ thống thông tin. Tuy nhiên, nhiệm vụ này đang gặp nhiều khó khăn trong triển khai diện rộng do thiếu hụt đội ngũ chuyên gia kiểm thử chất lượng ở các cấp độ khác nhau. Trong khuôn khổ bài báo này, chúng tôi trình bày nghiên cứu phát triển Framework có khả năng tự động trinh sát thông tin và tự động lựa chọn các mã để tiến hành khai thác mục tiêu dựa trên công nghệ học tăng cường (Reinforcement Learning). Bên cạnh đó Framework còn có khả năng cập nhật nhanh các phương pháp khai thác lỗ hổng bảo mật mới, hỗ trợ tốt cho các cán bộ phụ trách hệ thống thông tin nhưng không phải là chuyên gia bảo mật có thể tự động đánh giá hệ thống của mình, nhằm giảm thiểu nguy cơ từ các cuộc tấn công mạng. Abstract—Currently, security assessment is one of the most important proplem in information security. Vulnerability assessment/exploitation should be performed regularly with different levels of complexity for each information system. However, this task is facing many difficulties in large-scale deployment due to the lack of experienced testing experts. In this paper, we proposed a Framework that can automatically gather information and automatically select suitable module to exploit the target based on reinforcement learning technology. Furthermore, our framework has intergrated many scanning tools, exploited tools that help pentesters doing their work. It also can be easily updated new vulnerabilities exploit techniques.

Predicting Security Vulnerable Developers Based On Their Techno-Behavioral Characteristics

Assigning developers for highly secured software projects requires identifying developers’ tendency to contribute towards vulnerable software codes called developer-centric security vulnerability to mitigate issues on human resource management, financial and project timelines. There are problems in assessing the previous codebases in evaluating the developer-centric security vulnerability level of each developer. Thus, this paper suggests a method to evaluate this through the techno-behavioral features of their previous projects. Consequently, we present results of an exploratory study of the developer-centric security vulnerability level prediction using a dataset of 1827 developers by logically selecting 13 techno-behavioral features. Our results depict that there is a correlation between techno-behavioral features and developer-centric security vulnerability with 89.46% accuracy. This model enables to predict developer-centric security vulnerability level of any developer if the required techno-behavioral features are available avoiding the analysis of his/her previous codebases.

Wireless communication network security intelligent monitoring system based on machine learning

Aiming at the problems of traditional wireless communication network security vulnerability monitoring systems such as low monitoring accuracy and time-consuming, a machine learning-based intelligent monitoring system for wireless communication network security vulnerabilities is proposed. In the hardware design of the monitoring system, based on the overall architecture of the wireless communication network and the data characteristics of the wireless communication network, it is divided into a vulnerability data collection module, a vulnerability data scanning module, and a network security vulnerability intelligent monitoring module. In the vulnerability data collection module, the wireless data collector is used to collect vulnerability data in the vulnerability database, and according to the attributes of the vulnerability data, the XSS vulnerability detection plug-in is connected to the vulnerability scanner to scan for wireless communication network vulnerabilities; When the communication network vulnerability data signal is traced, the system session operation of monitoring the vulnerability data. The software part introduces the neural network algorithm in the machine learning intelligent algorithm to process the hidden data in the security vulnerability data. The experimental results show that the wireless communication network security vulnerability intelligent monitoring system based on machine learning can effectively improve the system monitoring accuracy and the efficiency of wireless communication network security vulnerability monitoring.