A two-sided experiment of intrusion detection, attack and defense, based on adversarial adaptive-domain transfer learning is designed. Based on the scientific research results, this experiment proposes an idea to improve the migration capability by adding domain alignment at different stages of a transfer learning model, and using the enhanced domain loss evaluation function to realize the knowledge transfer of intrusion detection and defense. In the experiment, students are organized as two groups to simulate an “attack and defense” scenario. One group uses adversarial neural networks to implement network attack data forgery and the other uses transfer learning intrusion detection knowledge to protect the system. The scenario is conducive to students to deeply grasp the frontier technology and development trend of intrusion detection and transfer learning.
- Article type
- Year
- Co-author
Open Access
Issue
In this paper, we propose a Multi-granularity Spatial Access Control (MSAC) model, in which multi-granularity spatial objects introduce more types of policy rule conflicts than single-granularity objects do. To analyze and detect these conflicts, we first analyze the conflict types with respect to the relationship among the policy rules, and then formalize the conflicts by template matrices. We designed a model-checking algorithm to detect potential conflicts by establishing formalized matrices of the policy set. Lastly, we conducted experiments to verify the performance of the algorithm using various spatial data sets and rule sets. The results show that the algorithm can detect all the formalized conflicts. Moreover, the algorithm’s efficiency is more influenced by the spatial object granularity than the size of the rule set.
京公网安备11010802044758号