The analysis of the decoding failure rate of the bit-flipping algorithm has received increasing attention. For a binary linear code we consider the minimum number of rows in a parity-check matrix such that the bit-flipping algorithm is able to correct errors up to the minimum distance without any decoding failures. We initiate a study of this bit-flipping redundancy, which is akin to the stopping set, trapping set or pseudocodeword redundancy of binary linear codes, and focus in particular on codes based on finite geometries.