Generative Diffusion Models for Secure UAV-ISAC with Real-Time Target Tracking

Abstract

Unmanned aerial vehicle (UAV) platforms with integrated sensing and communication (ISAC) are prime candidates for surveillance missions, in which a dual-function drone tracks a mobile target and alerts a ground station when the target enters a protected region. Such alerts generate event-triggered communication traffic. By observing the change in the traffic, an eavesdropper (Eve) can therefore learn in real time whether the target is detected inside the protected region without decoding any message. Existing physical-layer security techniques protect the message content or hide that a transmission occurs, but the composition of the traffic remains exposed. We formulate the threat as traffic-composition covertness and propose a keyless diffusion-based transmission scheme that hides the triggered traffic. The scheme superposes the beamformed information streams of the UAV with a message-agnostic safeguard waveform generated by a conditional denoising diffusion implicit model. Training shapes the safeguard distribution such that triggered and non-triggered slots become statistically indistinguishable at Eve. The legitimate user shares no secret key with the UAV. We formulate the joint design as a rate maximization under covertness, reliability, and sensing constraints, with the sensing accuracy measured by the posterior Cramér-Rao bound (PCRB) of the beam-dependent tracking problem. Our numerical results show that, with multiple transmit antennas and an Eve signal-to-noise ratio (SNR) of $5$~dB, a learned Eve stays near the blind guess of $0.5$ for every safeguard beam split, a detector that knows the safeguard model reaches $0.71$ to $0.73$ inside Bob's main lobe and $0.53$ to $0.55$ outside it, while the average position PCRB varies only between $0.59$ and $0.70$~m$^2$.