Summary Broadband dielectric dispersion measurements are attractive options for the assessment of water-filled porosity. Dielectric permittivity is influenced by salinity as well as other rock/fluid properties. However, the effect of salinity on Maxwell-Wagner polarization (i.e., interfacial polarization) and dielectric permittivity in rock samples with complex pore structures requires further investigation. The objectives of this work are (a) to perform frequency-domain dielectric permittivity numerical simulations on 3D pore-scale rock samples at different salt concentration levels, (b) to quantify the effect of salinity on dielectric permittivity and interfacial polarization in the frequency range between 20 MHz and 5 GHz, and (c) to quantify the critical frequency (i.e., the frequency at which the relative permittivity becomes frequency-independent). We first perform pore-scale frequency domain dielectric permittivity simulations in fully water-saturated carbonate samples with complex pore structures to obtain the complex dielectric permittivity in the frequency range of 0.01–5 GHz and at different salinity levels. Next, we numerically create partially water/hydrocarbon-saturated water-wet samples and perform simulations at different salinity and water saturation levels to investigate the combined effect of salinity and water saturation on dielectric permittivity. Finally, we investigate how reliable conventional mixing models, such as the complex refractive index model (CRIM) and Hanai-Bruggeman (HB), are in the assessment of water saturation at different salinity levels. We used 3D pore-scale rock samples with complex pore structures from Austin Chalk, Estaillades Limestone, and Happy Spraberry formations. The increase in salinity from 2 to 50 parts per thousand (PPT) resulted in the relative permittivity to increase by 18% at 20 MHz. Similarly, an increase in salinity from 2 PPT to 50 PPT resulted in electrical conductivity to increase by 15 times at 20 MHz. However, at 5 GHz, the difference between the relative permittivity of the samples at different salinities was negligible. We demonstrated that the critical frequency was above 1 GHz. Thus, if complex dielectric permittivity at 1 GHz is being used, an accurate salinity assumption is required in the interpretation of conventional dielectric mixture models in carbonate formations. Finally, we observed 52% and 42% average relative errors in water saturation quantification when applying CRIM and HB models at all the frequencies of interest, respectively. The results also indicated that conventional models should not be used in the presence of uncertainty in salinity at lower frequencies. The results of this work quantified the frequency at which the water-filled pore volume rather than the Maxwell-Wagner polarization controls the relative permittivity of rock samples saturated with a wide range of brine salinity. Moreover, the results demonstrated that the relative permittivity of the rock samples with complex pore structures may still be significantly affected by the interfacial polarization even at 1 GHz. Moreover, the results suggested that the conventional mixture methods cannot reliably take into account the salt concentration of formation water, and this can lead to significant errors in reserves assessment.