Draw the Bayesian network for this problem. If we assume that the variables are not conditionally independent, what would be the number of independent parameters that is required to describe this joint distribution? If we observe the fourth evidence, (E4 = true), for which hacker do we gain information?
A cyber-security officer is investigating a cyber-crime case. The officer considers three hackers as the possible suspects in this case. The three hackers are H1, H2, H3, which are marginally independent from each other. There are four forensic evidences (E1, E2, E3, E4) which the officer wants to check for presence in order to find the most probable suspect based on the findings. The forensic evidences are conditionally dependent to the three hackers as they have known attack styles as follows: E1 depends only on H1, E2 depends on H1 and H2. E3 is depends on H1 and H3, whereas E4 depends only on H3. Assume all random variables are Boolean, they are either “true” or “false”.
-
Draw the Bayesian network for this problem.
-
If we assume that the variables are not conditionally independent, what would be the number of independent parameters that is required to describe this joint distribution?
-
If we observe the fourth evidence, (E4 = true), for which hacker do we gain information?
Trending now
This is a popular solution!
Step by step
Solved in 3 steps with 15 images
