We exploit the cross-reactivity of dengue (DENV) and zika (ZIKV) virus polyclonal antibodies for nonstructural protein 1 (NS1) to construct a selective sensor that can detect yellow fever virus (YFV) NS1 in a manner similar to chemical olfaction. DENV and ZIKV antibodies were screened for their ability to bind to DENV, ZIKV, and YFV NS1 by ELISA and in pairs in paper immunoassays. A strategic arrangement of antibodies immobilized on paper and conjugated to different colored gold NPs was used to distinguish the three biomarkers. Machine learning of test area RGB values showed that with two spots, readout accuracies of 100% and 87% were obtained for both pure NS1 and DENV/YFV mixtures, respectively. Additional image pre-processing allowed differentiation between all 4 DENV serotypes with 92% accuracy. The technique was extended to hack a commercial DENV test to detect YFV and ZIKV by augmentation with DENV and ZIKV polyclonal antibodies.2 KEYWORDS selective sensing, antibody cross reactivity, multicolor gold nanoparticles, machine learning, multiplexed sensing Diagnostic tools are key for responding to infectious disease outbreaks, because they provide critical information for patient care, resource allocation, disease containment, and public health surveillance. Point-of care (POC) diagnostics have gained attention for emergency situations because they are inexpensive, portable, operable by non-experts, and deliver results within minutes. 1,2 The most widely used POC diagnostics are paper-based lateral flow immunoassays, where a biological fluid is added to a paper strip. The fluid wicks through the strip by capillary action, 3-5 and two colored lines appear for a positive test, and one line for negative, which can be read out by eye. This color is due to the presence of gold nanoparticles (NPs) conjugated to the antibody raised against the target biomarker. 6 Paper-based immunoassays are valuable diagnostics in resource-limited settings. 7 While lab-based assays like PCR and ELISA have higher sensitivity and specificity, they are difficult to implement in fieldable, decentralized situations because they require electricity, lab infrastructure, experts to operate them, and cold chains for required reagents.With every new epidemic, diagnosis is essential during the initial outbreak period for disease containment and surveillance. Unfortunately, for new outbreaks, the necessary biological reagents for diagnosis are not yet available, and an explosive rise in infections can leave clinicians with limited recourse. 8 Generating new antibodies requires an enormous amount of time and money, where the entire process from selection to manufacturing takes 16-24 months with costs reaching $100M. 9, 10 In the 2014 Ebola and 2015 Zika outbreaks, even with concerted