Low-field nuclear magnetic resonance (LF NMR) parameters and fatty acid contents, combined with chemometrics, were employed to detect the adulteration of camellia oil (CAO) with various oils, including rapeseed oil (RO), sunflower oil (SSO), sesame oil (SEO), corn oil (COO), rice bran oil (RBO), peanut oil (PEO), palm superolein (PAO), or high oleic-peanut oil (HO-PEO). In principal component analysis (PCA), CAO was characterized by higher levels of C18:1n9 and S22, which differentiates it from other vegetable oils. Partial least squares-discriminant analysis (PLS-DA) revealed robust clustering among CAO and other samples. Adulterated CAO samples, with an adulteration level exceeding 10 %, could be accurately classified, achieving a total discrimination accuracy of over 97.15 %. Notably, when the adulteration rate surpassed 40 %, the recognition accuracy for all samples reached 100 %. The optimized partial least squares (PLS) models, relying on fewer than 18 potential key markers identified by variable importance in projection, demonstrated efficiency and precision in predicting the adulteration levels in CAO.