Controlling Elections by Replacing Candidates: Theoretical and Experimental Results

We consider elections where the chair may attempt to influence the result by replacing candidates with the intention to make a specific candidate lose (destructive control). We call this form of control “replacement control” and we study its computational complexity. We focus in particular on Plurality and Veto, for which we prove that destructive control via replacing candidates is computationally difficult, and Borda for which we prove that destructive control via replacing candidates is computationally easy. To get more insight into the practical complexity of this problem, we also perform an extensive experimental study. This study shows that the theoretical computational complexity results are often not reflecting the practical difficulty of controlling elections by replacing candidates.