Intrusion Detection Systems (IDS), are an essential component of Wireless Sensor Networks (WSN) since they monitor the integrity of the network and report any suspicious or illegal activity. WSNs are susceptible to a wide variety of security risks, some of the most common of which being malicious attacks, data manipulation, unauthorized access, and compromised nodes. Identifying and addressing these security issues is much easier with the assistance of an IDS. This paper presents a machine learning model for employing IDS in WSN using Histogram Gradient Boosting Classifier. The proposed model is able to capture intricate patterns and distributions in the data in an effective manner thanks to the use of histogram representations. In addition, since gradient boosting is an iterative process, the model is able to zero in on difficult-to-detect instances of infiltration, hence continually enhancing its detection skills. However, in order to obtain optimum performance, it is necessary to appropriately tune the hyperparameters and solve possible difficulties such as class imbalance or noisy data. The proposed IDS model classified different attacks with an accuracy of 93.7%.