A prominent paper on dishonesty relied on a fabricated dataset, and different fonts provide proof:
Perhaps the most peculiar feature of the dataset is the fact that the baseline data for Car #1 in the posted Excel file appears in two different fonts. Specifically, half of the data in that column are printed in Calibri, and half are printed in Cambria.
The analyses we have performed on these two fonts provide evidence of a rather specific form of data tampering. We believe the dataset began with the observations in Calibri font. Those were then duplicated using Cambria font.
Also mentioned in The Economist:
RISK: It's data, it's in Excel, therefore it must be correct.
not-a-RISK: Making your data publicly available is a good thing.
Source: The Economist via The Risks Digest 