Attack Prediction to Enhance Attack Path Discovery Using Improved Attack Graph

Organisations and governments constantly face potential security attacks. However, the need for next-generation cyber defence has become even more urgent in a day age when attack surfaces that hackers can exploit have grown at an alarming rate with increase number of devices are connected to Internet. As such, relies on predictive analysis is proactive than existing technologies rely intrusion detection. Many approaches which detect predict attacks been proposed recent times. One such approach graphs. The primary purpose graph not only but its next steps within network as well as. More specifically, depicts paths attacker may employ circumvent policies by exploiting interdependencies between vulnerabilities. extant graphs plagued few issues. Scalability just one main issues generation faces. This because used increases vulnerabilities network. This, turn, complexity amount time required generate graph. At present, studies subsequent during had manually assigned location analysis. In order overcome this limitation, present study recommends use intelligent agents reduce reachability calculating nodes using A* prune algorithm remove useless edges complexity. For analysis, random forest (RF) was detect, predict, dynamically ascertain results experiment revealed produced better