The atmospheric neutrino flux represents a natural source that can be exploited to infer properties about Cosmic Rays and neutrino oscillation physics. The JUNO observatory, a 20 kt liquid scintillator detector currently under construction in China, will be able to detect the atmospheric flux, given the large volume and the excellent energy resolution. In this study, a sample of atmospheric neutrinos Monte Carlo events has been generated from theoretical models and then processed by a full Geant4 - based simulation, which propagates all particles and light inside the detector. The different time evolution of light allows to discriminate the flavor of primary neutrinos. A probabilistic unfolding method has been used, in order to infer the primary neutrino energy spectrum from the detector output. The simulated spectrum has been reconstructed between 100 MeV and 10 GeV, showing a great potential of the detector in the atmospheric low energy region.