Ensuring consumer safety and regulatory compliance in tobacco products requires accurate detection and quantification of additives. While conventional techniques like gas chromatography – mass spectrometry (GC–MS) and liquid chromatography – mass spectrometry (LC–MS) are effective, they are often hindered by complex sample preparation, high costs, and lengthy analysis times. This study evaluates mid-infrared (MIR) and near-infrared (NIR) spectroscopy, combined with multivariate analysis, as rapid and cost-effective alternatives for additive detection in tobacco products. A representative set of tobacco samples was spiked with caffeine, menthol, glycerol, and cocoa, analysed with MIR and NIR, followed by data analysis using principal component analysis (PCA), hierarchical clustering analysis (HCA), partial least squares-discriminant analysis (PLS-DA), and soft independent modelling of class analogy (SIMCA). Unsupervised analysis (PCA and HCA) could effectively distinguish between spiked and non-spiked samples. Supervised classification models demonstrated high accuracy, with SIMCA achieving 87–100% correct classification and PLS-DA yielding 80–100% accuracy. Additionally, partial least squares (PLS) regression enabled a good quantitative estimation of additive concentrations, highlighting the importance of data preprocessing. Overall, NIR spectroscopy coupled with SIMCA provided the most robust classification models, making it the most effective technique for qualitative analysis. In contrast, MIR spectroscopy demonstrated superior performance in quantitative estimation. These findings underscore the potential of infrared spectroscopy as a fast, reliable, and cost-effective alternative to conventional methods for tobacco additive analysis [1].