[vaylian]

Bonferonni correction is relevant when you calculate multiple p-values. Most statistical tests are used with a p-value threshold of 5% to reject the null-hypothesis. But because you are repeatedly testing, the probability for false positives increases and that is why you need to decrease the threshold and make it harder, to obtain a p-value below that threshold to declare a significant result.

You typically use the Bonferroni correction when making general statements about a statistical relationship. You wouldn't use it for checking if a particular image shows illegal content. If you kept testing with your image classifier, your significance threshold would need to be continuously lowered and you would asymptotically reach zero.

Relevant XKCD: 882

[dtj1123]

No, I'm not referring to Bonferroni's correction, which obviously has nothing to do with what we're discussing. I'm sure I've heard this called Bonferroni's principle.

Edit: Yes, in the section 'Statistical Limits of Data Mining' in the book Mining of mMssive Data Sets it's called Bonferroni's principle.