Cloud computing has revolutionized IT infrastructure by providing scalable and cost-effective solutions. However, the shared nature of cloud environments introduces security risks, particularly co-resident attacks, where malicious virtual machines (VMs) exploit physical proximity to compromise neighboring VMs. Traditional Intrusion Detection Systems (IDS) struggle to detect such sophisticated attacks due to their dynamic and stealthy nature. This paper proposes an Artificial Intelligence (AI)-based IDS to mitigate co-resident attacks in cloud infrastructure. Leveraging machine learning (ML) techniques such as Deep Learning (DL) and Anomaly Detection, the proposed system analyzes resource usage patterns, network traffic, and side-channel signals to identify malicious co-residence. Experimental results on a simulated cloud environment demonstrate that the AI-based IDS achieves a detection accuracy of 98.5% with a low false-positive rate. The system also incorporates mitigation strategies such as VM migration and resource isolation to neutralize detected threats. This AI based security model (AE-LSTM-CNN) research contributes to enhancing cloud security by providing an adaptive and intelligent defense mechanism against co-resident attacks.