Sensor attacks on grid-tie photovoltaic (PV) inverters can cause severe damage. Considering uncertain environments and unknown model mismatches, real-time estimation and defense for sensor attacks on actual PV inverters are challenging. In this article, we propose an optimization-driven robust estimator within the attack frequency range using the H_∞ index, while the model mismatch effect on estimation is also minimized. To improve the real-time response under varying environments, an analytical solution from a convex quadratic programming reformulation is constructed. Guided by the estimation, we further develop a closed-loop compensation strategy with a tracking controller and a low-pass filter. Through code porting, our proposed defense strategy has been implemented in a microcommercial PV inverter. Hardware implementations show that our defense approach can effectively mitigate sensor attacks and maintain stable inverter operation.