Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

A methodology for Zero-Day Vulnerability Identification.

More »

Fig 1 Expand

Table 1.

DQN agent hyperparameters selection at the time of training.

More »

Table 1 Expand

Fig 2.

DQN agent training log with 1000 episodes and episode reward.

More »

Fig 2 Expand

Table 2.

DQN agent training statistics after completing 1000 episodes.

More »

Table 2 Expand

Fig 3.

Training Performance of DQN Agent with 1000 Episodes and Episode Steps.

More »

Fig 3 Expand

Fig 4.

DQN Agent Training Progress: Episode Rewards over 1000 Episodes.

More »

Fig 4 Expand

Fig 5.

Tracking the performance of a DQN agent over 1000 training episodes.

More »

Fig 5 Expand

Fig 6.

Measuring the Performance of DQN Agent in 1000 Training Episodes and average steps.

More »

Fig 6 Expand

Fig 7.

Training coverage of the agent.

More »

Fig 7 Expand

Fig 8.

DQN agent Training scatter plot.

More »

Fig 8 Expand

Table 3.

Training output sample data are taken from the DQN agent.

More »

Table 3 Expand

Fig 9.

DQN Agent Forecasting Progress: Episode Rewards after forecasted 1000 Episodes.

More »

Fig 9 Expand

Fig 10.

DQN Agent with 1000 training and 1000 forecasted Episode Steps Performance.

More »

Fig 10 Expand

Fig 11.

Performance of the DQN Agent: Episode Rewards after Predicted 1000 Episodes.

More »

Fig 11 Expand

Fig 12.

Performance of DQN agent over 1000 training episodes and 1000 forecasted episodes.

More »

Fig 12 Expand

Fig 13.

Measure Performance of DQN Agent Predicting Average Steps in 1000 Episodes.

More »

Fig 13 Expand

Table 4.

DQN agent Forecasting statistics after completing 1000 episodes.

More »

Table 4 Expand

Table 5.

Comparison of Reinforcement Learning Approaches in Cybersecurity Research.

More »

Table 5 Expand

Fig 14.

Visualization of the Relationships between Different Metrics in a Normalized and Scaled Forecast Statistics.

More »

Fig 14 Expand

Fig 15.

Comparison of Multiple Runs of Same Algorithm on the Same Dataset (Kaggle-RL).

More »

Fig 15 Expand

Fig 16.

Comparison of Multiple Runs of Same Algorithm on the Same Dataset (NSL-KDD).

More »

Fig 16 Expand

Fig 17.

Comparison of Multiple Runs of Same Algorithm on the Same Dataset (UNSW-NB15).

More »

Fig 17 Expand

Table 6.

Comparison of Deep Learning (DL), Traditional ML and Proposed RL Methodology (DQN).

More »

Table 6 Expand