Conclusions

With the popularization of the Internet, the rapid dissemination and sharing of information have been realized, which makes people's work and life more convenient and promotes the progress of the society. With the development of 3G, 4G and fiber optic broadband, the network speed has been greatly improved, the construction of enterprise informatization has been promoted, and the competitiveness of enterprises has been improved. However, while the Internet brings us convenience, there are also many security risks, such as website information leakage, software vulnerabilities, hacker attacks and other network threats, which bring serious economic losses to people. Therefore, accurate network security assessment and effective security defense strategy become very urgent and necessary.

In order to predict the possible attack path and make quantitative evaluation, this paper establishes an attack graph model based on neural network. In the attribute attack graph, an algorithm to eliminate the attack cycle is proposed, and a method to transform the acyclic attribute attack graph into a Bayesian network is proposed. This model takes network security state data as input, obtains all possible attack paths, and uses Bayesian formula to calculate the probability of each attack path, so as to quantitatively evaluate the vulnerability of the network. Network administrator according to the forecast results targeted to strengthen network security.

In this paper, the fault diagnosis of computer network is studied, and the computer network fault is simulated by using SOM method and BP neural network method. Based on the SOM neural network belonging to the self-organizing network of competitive learning, it is not necessary to specify in advance the fault type of training samples for the fault diagnosis of computer network, so it has good clustering ability. SOM neural network and BP neural network are effectively combined by adding weights, and LM algorithm is improved by using parallel algorithm. It is significant to diagnose by example.

Callback before_footer in local_aigrade component should be migrated to new hook callback for core\hook\output\before_footer_html_generation
  • line 7225 of /lib/moodlelib.php: call to debugging()
  • line 7292 of /lib/moodlelib.php: call to {closure}()
  • line 71 of /lib/classes/hook/output/before_footer_html_generation.php: call to get_plugins_with_function()
  • line 987 of /lib/classes/output/core_renderer.php: call to core\hook\output\before_footer_html_generation->process_legacy_callbacks()
  • line 154 of /mod/book/view.php: call to core\output\core_renderer->footer()