# Processing with AI ## Exploration : IA & Ethics Name: > Jason Wu > Subject: > Detect student presence in class using Face Recognition >[TOC] ## Design brief ### Biais If we don't source our dataset with enough rigor, the following biais might appear: >1. Wrong recognition of students >2. Possibility to get students and professors mixed up >3. Students could pose as anyone else We will ensure that our model is not biaised by: >1. Sourcing our data from a specific photoshoot of students at the beginning of the year >2. Making sure our data take into account the fact that a student couldn't be count more than once >3. Point out as many details of facial caracteristics as possible ### Overfitting We will make sure our model does not overfit by adding an evaluation system of the model and guarantee that the model will still detect the underlying relationship instead of focusing on errors. ### Misuse >We have to remind ourselves that our application could be misused by students to do fake profil recognition. ### Data leakage >In a catastrophic scenario, where all of our training dataset were stolen or recovered from our model, the risk would be that we wont be able to evaluate our students properly and people would know exactly when each student was school or not. ### 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 students could falsify their attendance.