One-Class SVM
A boundary learned from only normal training examples, flagging anything outside it as novel, without ever seeing an example of what abnormal looks like.
The nu parameter bounds the fraction of training points allowed to fall outside the boundary, trading a wide, forgiving fit against a tight, strict one — every setting trades detection rate against false-positive rate, with no choice improving both.
The method assumes the training data is clean, uncontaminated normal data; feeding it data with anomalies already mixed in teaches the boundary to consider those anomalies normal too.