The expansion of the Internet-of-Things (IoT) market is visible in homes, factories, public places, and smartcities. While the massive deployment of connected devices offers opportunities to improve quality of life andto develop new services, the impact of such devices on the security of the users in a context where the levelof malicious threat continues to increase is a major concern. One of the challenges is the heterogeneity andconstant evolution of wireless technologies and protocols used. To overcome this problem, we propose RIDS,aRadio Intrusion Detection Systemthat is based on the monitoring and profiling of radio communications atthe physical layer level using autoencoder neural networks. RIDS is independent of the wireless protocolsand modulation technologies used. Besides, it is designed to provide a threefold diagnosis of the detectedanomalies: temporal (start and end date of the detected anomaly), frequential (main frequency of the anomaly),and spatial (location of the origin of the anomaly). To demonstrate the relevance and the efficiency of ourapproach, we collected a large dataset of radio-communications recorded with three different probes deployedin an experimental room. Multiple real-world attacks involving a wide variety of communication technologiesare also injected to assess the detection and diagnosis efficiency. The results demonstrate the efficiency ofRIDS in detecting and diagnosing anomalies that occurred in the 400–500 Mhz and 800–900 Mhz frequencybands. It is noteworthy that compromised devices and attacks using these communication bands are generallynot easily covered by traditional solutions