You can look at moves as a series of probabilities. For each move, classify if it's more a blunder or inspired move and then look at people's games and see if they consistently have 1-2 moves that are much much better than their typical.
The problem is that at that level they're more likely to make the absolute perfect move than not. Super GMs often play 95-98%+ accuracy games.
But what if they only cheat occasionally? A top player would only need a handful of moves to go from say 3rd in a tournament to winning.