This study investigated the impact of artificial intelligent based embedded security solution model for PID controller. Recent studies have revealed that the conventional mitigation techniques like zoning, demilitarization, firewalls, company’s policies to mention but a few are no longer enough to match the sophisticated intelligence being deployed by attackers hence the urgent need for the adoption of artificial intelligent based embedded security solution model. Furthermore, conventional IT security solutions cannot be deployed directly in process controllers given the real time availability requirement of industrial control systems. This has limited the security solutions to firewalls, network segmentation and some laid down policies which the control system operators are not expected to violate. This study will ultimately help deliver algorithms that will be implemented in industrial field device controllers making them resilient to cyber-attacks whose consequences have far reaching implications. With regards to the methodology of the work, four sets of data were collected from the test bed. The first data, Data_1, shown in appendix D is the plant’s response to the existing PID algorithm. This was done by taking the temperatures of the plant at interval of 3 seconds after loading the controller with the existing (insecure) PID algorithm shown in appendix A. A total of 100 samples were taken. From the methodology employed, it was discovered that it is seen that the existing PID algorithm was able to achieve the control objective of maintaining the temperature of the process plant within the temperature range of 38 o C and 43 o C with 40 o C as the optimal or ideal performance. From table I in appendix I, the mean steady state error (MSSE) of the existing PID algorithm considering the 27th to 101th temperature data is 0.062631579 which is approximately 0.06. It means the accuracy of the existing PID algorithm is ((40 – 0.06)/40) ∗ 100 = 99. 85 %. This showed that the existing PID control algorithm’s performance is acceptable under normal condition since the minimum control accuracy required to achieve the control objective in the considered process plant is (40 – (3-2)/2)/40) ∗ 100 = 98. 75 %.