Abstract: The rise of quantum utility in the realm of quantum computing presents not just challenges but also significant opportunities for enhancing network security. This paradigm shift in computational capabilities allows for the development of advanced solutions to counteract the rapidly evolving nature of network attacks. Capitalizing on this technological advancement, this work introduces qIDS, an Intrusion Detection System (IDS) that innovatively integrates quantum and classical computing approaches. qIDS leverages Quantum Machine Learning (QML) techniques to effectively learn network behaviors and identify malicious activities. By conducting comprehensive experimental evaluations on public datasets, we demonstrate the proficiency of qIDS in attack detection, excelling in both binary and multiclass classification tasks. Our findings reveal that qIDS competes favorably with classical Machine Learning methods, highlighting the potential of quantum-enhanced cybersecurity solutions in the era of quantum utility.