Video streaming is the killer application of the Internet today. In this paper, we address the problem of realtime, passive Quality-of-Experience (QoE) monitoring of HTTP Adaptive Video Streaming (HAS), from the Internet-Service-Provider (ISP) perspective-i.e., relying exclusively on innetwork traffic measurements. Given the wide adoption of endto-end encryption, we resort to machine-learning (ML) models to estimate multiple key video-QoE indicators (KQIs) from the analysis of the encrypted traffic. We present ViCrypt, an MLdriven monitoring solution able to infer the most important KQIs for HTTP Adaptive Streaming (HAS), namely stalling, initial delay, video resolution, and average video bitrate. ViCrypt performs estimations in real-time, during the playback of an ongoing video-streaming session, with a fine-grained temporal resolution of just one second. For this, it relies on lightweight, stream-like features continuously extracted from the encrypted stream of packets. Empirical evaluations on a large and heterogeneous corpus of YouTube measurements show that ViCrypt can infer the targeted KQIs with high accuracy, enabling largescale passive video-QoE monitoring and proactive QoE-aware traffic management. Different from the state of the art, and besides real-time operation, ViCrypt is not bound to coarsegrained KQI-classes, providing better and sharper insights than other solutions. Finally, ViCrypt does not require chunk-detection approaches for feature extraction, significantly reducing the complexity of the monitoring approach, and potentially improving on generalization to different HAS protocols used by other videostreaming services such as Netflix and Amazon.