Earlier work examining susceptibility to visual illusions in autism has reported discrepant findings. Some of this research suggests that global processing is affected in autism while some of this research suggests otherwise. The discrepancies may relate to compliance issues and differences in population samples in terms of symptom severity, cognitive ability, and co-morbid disorders. Equally important, most of this work tended to treat global processing as if it were a singular construct, invoking similar cognitive operations across different visual illusions. We argue that this is not a fair assumption to make given the extensive research that has classified visual illusions on the basis of their cognitive demands. With this in mind, and to overcome the many caveats associated with examining a heterogeneous disorder such as autism directly, we examined how susceptibility to various illusions relates differently to people's scores on the Autism Spectrum Quotient (AQ) questionnaire. We found that susceptibility to the Muller-Lyer but not to the Ebbinghaus and Ponzo illusions decreased as a function of AQ and that the relationship between AQ and susceptibility to the Muller-Lyer illusion was different from those between AQ and susceptibility to the Ebbinghaus and Ponzo illusions. Our findings confirm that the cognitive operations underlying global processing in the Muller-Lyer illusion are different from the other illusions and, more importantly, reveal that they might be affected in autism. Future brain mapping studies could provide additional insight into the neural underpinnings of how global processing might and might not be affected in autism.