# Processing with AI ## Exploration : IA & Ethics Name: >Fair Play Problematic: > How to catch the unfair performance 100% correctly in the staduim? Small description of the project: > During the match, some players or fans maybe do some discriminate action. We need to detect them as soon as possible and catch them once happened. But the corrective is the problem. >[TOC] ## Design brief ### Biais If we don't source our dataset with enough rigor, the following biais might appear: >1. We ignore some bad actions >2. We do some mistake in some cases We will ensure that our model is not biaised by: >1. Sourcing our data from different points of cameras >2. Making sure more than 3 people need to confirm the video ### Overfitting We will make sure our model does not overfit by > Checking the video several times and make sure the rules ### Misuse >We have to remind ourselves that our application could be misused by clear rules and punishment system. ### Data leakage *Choose the most relevant proposition:* >In a catastrophic scenario, where all of our training dataset were stolen or recovered from our model, the risk would be lower. We need to keep the source safety. ### Hacking > If someone found a way to "cheat" our model and make it make any prediction that it want instead of the real one, the risk would be that we need to copy the video and delete the original one.