Stratospheric aerosol injection (SAI has been proposed as a potential method for mitigating risks and impacts associated with anthropogenic climate change. One such risk is widespread permafrost thaw and associated carbon release. While permafrost has been shown to stabilize under different SAI scenarios, natural variability may lead to a wide range of projected climate futures under SAI. Here we use the 10-member ensemble from the ARISE-SAI-1.5 simulations to assess the spread in projected active layer depth and permafrost temperature across boreal permafrost soils and specifically in four peatland and Yedoma regions. The forced response in active layer depth and permafrost temperature quickly diverge between an SAI and non-SAI world, but individual ensemble members overlap for several years following SAI deployment. Projected permafrost variability may mask the forced response to SAI and make it difficult to detect if and when SAI is stabilizing permafrost in any single realization. We find that it may take more than a decade of SAI deployment to detect the effects of SAI on permafrost temperature and almost 30 years to detect its effects on active layer depth. Not only does natural variability make it more difficult to detect SAI’s influence, it could also affect the likelihood of reaching a permafrost tipping point. In some realizations, SAI fails to prevent a tipping point that is also reached in a non-SAI world. Our results underscore the importance of accounting for natural variability in assessments of SAI’s potential influence on the climate system.