diff --git a/README.md b/README.md
index 22f5d5c..f387728 100644
--- a/README.md
+++ b/README.md
@@ -8,7 +8,7 @@ Repository of differentially-private methods for learning from features.
 
 
 ## Private Prototype Calculation
-1. Set your total privacy budget in (0,rho)-cZDP.
+1. Set your total privacy budget in (0,rho)-zCDP.
 2. Divide your total budget into a budget per step. Good starting values are listed below. The algorithm will perform `len(Ps)` many steps.
 
 ```python
diff --git a/src/dp_learning_ff/prototypes.py b/src/dp_learning_ff/prototypes.py
index b23183b..1ff9031 100644
--- a/src/dp_learning_ff/prototypes.py
+++ b/src/dp_learning_ff/prototypes.py
@@ -38,7 +38,7 @@ def give_private_prototypes(
     Args:
         train_preds (np.ndarray): (n, d)-array containing the predictions of the training set.
         train_targets (np.ndarray): (n, )-array containing the labels of the training set.
-        Ps (np.ndarray[float]): Array of privacy budget per step in (0,rho)-cZDP. To total privacy cost is the sum of this array. The algorithm will perform len(Ps) steps.
+        Ps (np.ndarray[float]): Array of privacy budget per step in (0,rho)-zCDP. To total privacy cost is the sum of this array. The algorithm will perform len(Ps) steps.
         seed (int): RNG seed
         subsampling (float): Ratio in (0, 1] of samples to use