The goal of this paper is to detect a change in observations quickly and more importantly its application to localization using time difference. The change point detection problem with sequential observations is called sequential detection or quickest detection. In the assumed model, distributed sensors are considered to be monitoring a system in which an abrupt change caused by a jamming signal occurs at some unknown time. We propose a framework using the quickest detection with cumulative sum (CUSUM) test which is well-known to be optimal for a non-Bayesian statistical change-point detection formulation. At each time, the distributed sensors decide about the presence or absence of any jamming signal. Once the sensors get a decision and transmit it to fusion center, then fusion center localizes the jammer. In the end, the results are evaluated using computer simulations.