Mobile small cells enabled by Network Coding (NC) are seen as a viable solution for 5G networks that can span the urban environment by being put up on demand anywhere and at any time across any device. Despite the advantages that NC-enabled mobile small cells provide to the 5G of mobile networks, there are some security threats (due to their vulnerabilities) owing to pollution attacks, in which intermediate nodes are used to tamper with packets in transit. Due to these polluted packets Erroneous decoding will occur at the receivers end. Detecting the polluted packets in NC enabled mobile small cell is a challenging task. The proposed An Adaptable Variable Homomorphic MAC based Intrusion Detection System (AV-H-MAC-IDS) effectively detects the polluted packets in the NC-enabled small cell environment. This model consists of different stages like region –based node clustering, node registration, homomorphic key-pair generation, and pollution attack detection. This method analyses the data of each node in the network to check whether data is altered or not. Due to region based clusters, it can effectively identify the attacker and their neighbours. Next to detection, it labels the nodes such that the malicious nodes can be isolated in subsequent data transmissions. This approach not only detects polluted packets, but also identifies the attacker's location, so that future packet pollution can be avoided up to some extent. It has been demonstrated that the proposed model outperforms both the state-of-the-art models and the more conventional models in terms of detection accuracy and time complexity.