final curiousity experiments

Tune.py

@@ -62,6 +62,7 @@ def prepare_data_and_model_environment():
     # get Cuda or CPU.
     device = get_device()
     dataset_name = Set_Name.CASIAFACES
+    # we are changing this sample size if we use CASIA Set
     if dataset_name == Set_Name.CASIAFACES:
         SAMPLE_SIZE = 400
         TRAINING_SAMPLE = 320
@@ -259,7 +260,7 @@ def run_unlearning_and_strategy_eval(env_dict, forget_class_idx, strategy, evalu
 # entry
 if __name__ == "__main__":
 
-    outer_loop = 20
+    outer_loop = 2
 
     inner_loop = CLASS_SIZE
     
@@ -301,7 +302,7 @@ if __name__ == "__main__":
             # WF-Net
             weight_filtration = WeightFiltration(
                 target_class_index=0,      #arch  ResNet18  GoogLeNet/Inception
-                epochs=6,                       #   
+                epochs=8,                       #   
                 lr=250.0, # ResNet18 = 150      #      150        100
                 gamma=0.001,                    #    0.001      
                 lambda_1=30,                 #       25        100
@@ -319,8 +320,8 @@ if __name__ == "__main__":
 
             strategies = [
                 #retrain,
-                linear_filtration,
+                #linear_filtration,
-                #weight_filtration,
+                weight_filtration,
                 #certified_unlearning,
             ]
             suite_runner = UnlearningAttack(arch=ARCH, class_size=CLASS_SIZE)
@@ -341,7 +342,7 @@ if __name__ == "__main__":
                         # if we are finetuning, no need to evaluate base model. 
                         # or may be never when not either!
                         evaluate = not finetuning,
-                        suite_runner=suite_runner
+                        #suite_runner=suite_runner
                     )
 
 

eval/UnlearningAttack.py

@@ -195,6 +195,13 @@ class UnlearningAttack:
                     # out
                     out_filtered = out_filtered[:,mask]
                     out_naive = out_naive[:, mask]
+
+                # testin masked
+                mask = torch.ones(out_filtered.shape[1], dtype = torch.bool, device = device)
+                mask[target_class] = False
+                # out
+                out_filtered = out_filtered[:,mask]
+                out_naive = out_naive[:, mask]
                 
                 filtered_logits.append(out_filtered)
                 naive_logits.append(out_naive)
@@ -225,7 +232,7 @@ class UnlearningAttack:
         # load from disk if saved model available
         target_dir = os.path.join("reports", framework_name)
         os.makedirs(target_dir, exist_ok=True)
-        current_log_file = os.path.join(target_dir, "attack_values.csv")
+        current_log_file = os.path.join(target_dir, "values.csv")
         
         if not os.path.exists(current_log_file):
             with open(current_log_file, "w") as f:

reports/CertifiedUnlearning/ResNet/time_metrics.txt

@@ -364,3 +364,105 @@ execution_time_sec
 395.553217
 395.613947
 395.703417
+399.307575
+398.598795
+396.550026
+395.576438
+395.851829
+395.795415
+395.707795
+395.629891
+395.795039
+395.628430
+395.666368
+395.595025
+395.616317
+396.976942
+398.485347
+398.770628
+395.566346
+395.587430
+395.693323
+395.949030
+395.609925
+395.700236
+395.667704
+395.740308
+395.847255
+395.762269
+396.040289
+395.934298
+395.752498
+395.790092
+395.815014
+395.673979
+395.635307
+395.753562
+395.636638
+398.120495
+395.658986
+395.638111
+395.624901
+396.023332
+395.663261
+395.755483
+395.827031
+395.619311
+395.763937
+395.706366
+397.424467
+395.719804
+395.680957
+395.752995
+395.715297
+395.740110
+395.876237
+395.703729
+395.732901
+395.650592
+395.705072
+395.656511
+395.729247
+395.677073
+395.631320
+395.759670
+395.826804
+395.648125
+395.855436
+395.838618
+395.741877
+395.777094
+396.006137
+395.836674
+396.084435
+395.693749
+395.775519
+395.801058
+395.754723
+395.796176
+396.015392
+395.843593
+395.991532
+395.765857
+395.850749
+395.807940
+395.919723
+396.945919
+395.718046
+395.723669
+395.784811
+395.939310
+395.697693
+395.775568
+395.833570
+395.910674
+395.994757
+395.884553
+395.940873
+395.802436
+395.810863
+399.934530
+396.091092
+395.880035
+395.704713
+402.741850

reports/CertifiedUnlearning/values.csv

@@ -0,0 +1,103 @@
+target_class, parameter_mia_accuracy, lookalike_accuracy, A-Dist, JS-Dist
+0,0.500000,0.829167, 0.020833, 0.635532
+1,0.500000,0.197917, 0.104167, 0.451290
+2,0.500000,0.454167, 0.093750, 0.492340
+3,0.500000,0.650000, 0.062500, 0.453693
+4,0.500000,0.258333, 0.343750, 0.575972
+5,0.500000,0.585417, 0.281250, 0.562983
+6,0.500000,0.256250, 0.302083, 0.465092
+7,0.500000,0.550000, 0.177083, 0.511510
+8,0.500000,0.331250, 0.072917, 0.473632
+9,0.500000,0.985417, 0.343750, 0.725261
+10,0.500000,1.000000, 0.031250, 0.633027
+11,0.500000,0.820833, 0.208333, 0.578812
+12,0.500000,0.756250, 0.239583, 0.636515
+13,0.500000,0.987500, 0.052083, 0.668559
+14,0.500000,0.270833, 0.010417, 0.467717
+15,0.500000,0.252083, 0.083333, 0.540191
+16,0.500000,0.385417, 0.114583, 0.470983
+17,0.500000,0.322917, 0.135417, 0.487943
+18,0.500000,0.487500, 0.031250, 0.492180
+19,0.500000,0.547917, 0.041667, 0.575168
+0,0.500000,0.950000, 0.208333, 0.655901
+1,0.500000,0.206250, 0.083333, 0.517121
+2,0.500000,0.387500, 0.125000, 0.505111
+3,0.500000,0.827083, 0.166667, 0.552245
+4,0.500000,0.256250, 0.281250, 0.575184
+5,0.500000,0.562500, 0.270833, 0.548510
+6,0.500000,0.252083, 0.270833, 0.532519
+7,0.500000,0.429167, 0.000000, 0.543832
+8,0.500000,0.204167, 0.145833, 0.511732
+9,0.500000,0.437500, 0.052083, 0.558003
+10,0.500000,1.000000, 0.104167, 0.707821
+11,0.500000,0.743750, 0.114583, 0.602524
+12,0.500000,0.477083, 0.125000, 0.515099
+13,0.500000,0.987500, 0.135417, 0.742003
+14,0.500000,0.322917, 0.104167, 0.490033
+15,0.500000,0.329167, 0.041667, 0.540890
+16,0.500000,0.962500, 0.166667, 0.475392
+17,0.500000,0.372917, 0.083333, 0.455598
+18,0.500000,0.527083, 0.072917, 0.537237
+19,0.500000,0.252083, 0.166667, 0.484630
+0,0.500000,0.979167, 0.125000, 0.703407
+1,0.500000,0.116667, 0.177083, 0.500014
+2,0.500000,0.360417, 0.104167, 0.497060
+3,0.500000,0.947917, 0.250000, 0.599938
+4,0.500000,0.283333, 0.312500, 0.582296
+5,0.500000,0.927083, 0.041667, 0.610601
+6,0.500000,0.277083, 0.343750, 0.515391
+7,0.500000,0.495833, 0.041667, 0.470818
+8,0.500000,0.356250, 0.114583, 0.542806
+9,0.500000,0.993750, 0.229167, 0.732571
+10,0.500000,1.000000, 0.052083, 0.632766
+11,0.500000,0.712500, 0.208333, 0.551207
+12,0.500000,0.193750, 0.239583, 0.412040
+13,0.500000,0.993750, 0.135417, 0.677506
+14,0.500000,0.354167, 0.177083, 0.462473
+15,0.500000,0.285417, 0.114583, 0.545430
+16,0.500000,0.454167, 0.218750, 0.527519
+17,0.500000,0.285417, 0.104167, 0.480010
+18,0.525000,0.666667, 0.166667, 0.539912
+19,0.500000,0.633333, 0.239583, 0.502165
+0,0.500000,0.637500, 0.010417, 0.580623
+1,0.500000,0.202083, 0.135417, 0.490814
+2,0.500000,0.275000, 0.000000, 0.520270
+3,0.500000,0.500000, 0.166667, 0.401563
+4,0.500000,0.597917, 0.062500, 0.588209
+5,0.500000,0.991667, 0.020833, 0.682998
+6,0.500000,0.222917, 0.302083, 0.515843
+7,0.500000,0.281250, 0.156250, 0.557951
+8,0.500000,0.191667, 0.052083, 0.457328
+9,0.500000,0.987500, 0.208333, 0.676620
+10,0.500000,1.000000, 0.166667, 0.723199
+11,0.500000,0.958333, 0.062500, 0.681015
+12,0.500000,0.495833, 0.208333, 0.518211
+13,0.500000,0.993750, 0.062500, 0.696251
+14,0.500000,0.283333, 0.104167, 0.480926
+15,0.500000,0.287500, 0.114583, 0.535151
+16,0.500000,0.704167, 0.218750, 0.475464
+17,0.500000,0.368750, 0.145833, 0.462922
+18,0.518750,0.489583, 0.166667, 0.549473
+19,0.500000,0.366667, 0.093750, 0.511173
+0,0.500000,0.993750, 0.072917, 0.674594
+1,0.500000,0.208333, 0.104167, 0.509519
+2,0.500000,0.200000, 0.083333, 0.554513
+3,0.500000,0.639583, 0.072917, 0.472225
+4,0.500000,0.272917, 0.250000, 0.572284
+5,0.500000,0.995833, 0.125000, 0.645992
+6,0.500000,0.289583, 0.156250, 0.505494
+7,0.500000,0.329167, 0.125000, 0.562745
+8,0.500000,0.506250, 0.072917, 0.586938
+9,0.500000,0.647917, 0.093750, 0.621831
+10,0.500000,1.000000, 0.260417, 0.760782
+11,0.500000,0.708333, 0.104167, 0.595735
+12,0.500000,0.447917, 0.239583, 0.414643
+13,0.500000,0.954167, 0.104167, 0.513961
+14,0.500000,0.318750, 0.208333, 0.476281
+15,0.500000,0.320833, 0.062500, 0.540674
+16,0.500000,0.589583, 0.156250, 0.525595
+17,0.500000,0.295833, 0.052083, 0.456003
+18,0.500000,0.612500, 0.104167, 0.526532
+19,0.500000,0.362500, 0.041667, 0.469123
+0,0.500000,0.852083, 0.145833, 0.652528
+1,0.500000,0.185417, 0.052083, 0.504167

reports/LinearFiltration/RESNET34/forget.csv

@@ -471,3 +471,5 @@ accuracy,macro_precision,macro_recall,macro_f1,weighted_precision,weighted_recal
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000

reports/LinearFiltration/RESNET34/forget_train.csv

@@ -471,3 +471,5 @@ accuracy,macro_precision,macro_recall,macro_f1,weighted_precision,weighted_recal
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000

reports/LinearFiltration/RESNET34/retain.csv

@@ -471,3 +471,5 @@ accuracy,macro_precision,macro_recall,macro_f1,weighted_precision,weighted_recal
 0.9520,0.9538,0.9520,0.9523,0.9538,0.9520,0.9523
 0.9539,0.9554,0.9539,0.9542,0.9554,0.9539,0.9542
 0.9526,0.9544,0.9526,0.9529,0.9544,0.9526,0.9529
+0.9526,0.9541,0.9526,0.9529,0.9541,0.9526,0.9529
+0.9533,0.9551,0.9533,0.9536,0.9551,0.9533,0.9536

reports/LinearFiltration/ResNet/time_metrics.txt

@@ -439,3 +439,5 @@ execution_time_sec
 0.001898
 0.001888
 0.001884
+1.632938
+0.001915

reports/WeightFiltration/RESNET34/forget.csv

@@ -471,3 +471,45 @@ accuracy,macro_precision,macro_recall,macro_f1,weighted_precision,weighted_recal
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0125,1.0000,0.0125,0.0247,1.0000,0.0125,0.0247
+0.1375,1.0000,0.1375,0.2418,1.0000,0.1375,0.2418
+0.0125,1.0000,0.0125,0.0247,1.0000,0.0125,0.0247
+0.2125,1.0000,0.2125,0.3505,1.0000,0.2125,0.3505
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0125,1.0000,0.0125,0.0247,1.0000,0.0125,0.0247
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0875,1.0000,0.0875,0.1609,1.0000,0.0875,0.1609
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0375,1.0000,0.0375,0.0723,1.0000,0.0375,0.0723
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0125,1.0000,0.0125,0.0247,1.0000,0.0125,0.0247
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0625,1.0000,0.0625,0.1176,1.0000,0.0625,0.1176
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000

reports/WeightFiltration/RESNET34/forget_train.csv

@@ -471,3 +471,45 @@ accuracy,macro_precision,macro_recall,macro_f1,weighted_precision,weighted_recal
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
 0.0031,1.0000,0.0031,0.0062,1.0000,0.0031,0.0062
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.1219,1.0000,0.1219,0.2173,1.0000,0.1219,0.2173
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.2375,1.0000,0.2375,0.3838,1.0000,0.2375,0.3838
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0063,1.0000,0.0063,0.0124,1.0000,0.0063,0.0124
+0.0031,1.0000,0.0031,0.0062,1.0000,0.0031,0.0062
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0437,1.0000,0.0437,0.0838,1.0000,0.0437,0.0838
+0.0031,1.0000,0.0031,0.0062,1.0000,0.0031,0.0062
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0719,1.0000,0.0719,0.1341,1.0000,0.0719,0.1341
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0094,1.0000,0.0094,0.0186,1.0000,0.0094,0.0186
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0094,1.0000,0.0094,0.0186,1.0000,0.0094,0.0186
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0094,1.0000,0.0094,0.0186,1.0000,0.0094,0.0186
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0125,1.0000,0.0125,0.0247,1.0000,0.0125,0.0247
+0.0063,1.0000,0.0063,0.0124,1.0000,0.0063,0.0124
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
+0.0437,1.0000,0.0437,0.0838,1.0000,0.0437,0.0838
+0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000

reports/WeightFiltration/RESNET34/retain.csv

@@ -471,3 +471,45 @@ accuracy,macro_precision,macro_recall,macro_f1,weighted_precision,weighted_recal
 0.9559,0.9566,0.9559,0.9560,0.9566,0.9559,0.9560
 0.9566,0.9574,0.9566,0.9567,0.9574,0.9566,0.9567
 0.9559,0.9571,0.9559,0.9561,0.9571,0.9559,0.9561
+0.9513,0.9536,0.9513,0.9517,0.9536,0.9513,0.9517
+0.9520,0.9540,0.9520,0.9523,0.9540,0.9520,0.9523
+0.9513,0.9536,0.9513,0.9517,0.9536,0.9513,0.9517
+0.9520,0.9542,0.9520,0.9524,0.9542,0.9520,0.9524
+0.9513,0.9523,0.9513,0.9514,0.9523,0.9513,0.9514
+0.9539,0.9557,0.9539,0.9542,0.9557,0.9539,0.9542
+0.9586,0.9605,0.9586,0.9589,0.9605,0.9586,0.9589
+0.9566,0.9584,0.9566,0.9568,0.9584,0.9566,0.9568
+0.9526,0.9545,0.9526,0.9530,0.9545,0.9526,0.9530
+0.9487,0.9518,0.9487,0.9493,0.9518,0.9487,0.9493
+0.9539,0.9552,0.9539,0.9541,0.9552,0.9539,0.9541
+0.9526,0.9539,0.9526,0.9529,0.9539,0.9526,0.9529
+0.9553,0.9566,0.9553,0.9555,0.9566,0.9553,0.9555
+0.9539,0.9561,0.9539,0.9543,0.9561,0.9539,0.9543
+0.9500,0.9518,0.9500,0.9503,0.9518,0.9500,0.9503
+0.9533,0.9547,0.9533,0.9535,0.9547,0.9533,0.9535
+0.9546,0.9558,0.9546,0.9547,0.9558,0.9546,0.9547
+0.9513,0.9532,0.9513,0.9516,0.9532,0.9513,0.9516
+0.9493,0.9516,0.9493,0.9497,0.9516,0.9493,0.9497
+0.9513,0.9536,0.9513,0.9516,0.9536,0.9513,0.9516
+0.9520,0.9533,0.9520,0.9521,0.9533,0.9520,0.9521
+0.9533,0.9545,0.9533,0.9535,0.9545,0.9533,0.9535
+0.9513,0.9536,0.9513,0.9517,0.9536,0.9513,0.9517
+0.9520,0.9538,0.9520,0.9523,0.9538,0.9520,0.9523
+0.9513,0.9523,0.9513,0.9514,0.9523,0.9513,0.9514
+0.9533,0.9551,0.9533,0.9536,0.9551,0.9533,0.9536
+0.9572,0.9590,0.9572,0.9576,0.9590,0.9572,0.9576
+0.9566,0.9583,0.9566,0.9568,0.9583,0.9566,0.9568
+0.9533,0.9551,0.9533,0.9536,0.9551,0.9533,0.9536
+0.9500,0.9529,0.9500,0.9506,0.9529,0.9500,0.9506
+0.9553,0.9565,0.9553,0.9554,0.9565,0.9553,0.9554
+0.9520,0.9534,0.9520,0.9522,0.9534,0.9520,0.9522
+0.9546,0.9562,0.9546,0.9549,0.9562,0.9546,0.9549
+0.9526,0.9547,0.9526,0.9530,0.9547,0.9526,0.9530
+0.9507,0.9524,0.9507,0.9509,0.9524,0.9507,0.9509
+0.9533,0.9547,0.9533,0.9535,0.9547,0.9533,0.9535
+0.9546,0.9558,0.9546,0.9547,0.9558,0.9546,0.9547
+0.9520,0.9539,0.9520,0.9522,0.9539,0.9520,0.9522
+0.9493,0.9515,0.9493,0.9496,0.9515,0.9493,0.9496
+0.9520,0.9542,0.9520,0.9523,0.9542,0.9520,0.9523
+0.9520,0.9531,0.9520,0.9520,0.9531,0.9520,0.9520
+0.9539,0.9552,0.9539,0.9541,0.9552,0.9539,0.9541

reports/WeightFiltration/ResNet/time_metrics.txt

@@ -439,3 +439,148 @@ execution_time_sec
 0.000431
 0.000414
 0.000410
+86.130236
+0.001228
+0.001707
+0.000427
+0.000437
+0.000431
+0.000433
+0.000433
+0.000436
+0.000414
+0.000429
+0.000409
+0.000436
+0.000419
+0.000398
+0.000426
+0.000420
+0.000440
+0.000432
+0.000425
+86.256719
+0.000429
+0.000429
+0.000423
+0.000428
+0.000441
+0.000430
+0.000443
+0.000432
+0.000425
+0.000428
+0.000437
+0.000426
+0.000431
+0.000434
+0.000437
+0.000433
+0.000428
+0.000436
+0.000429
+86.242122
+0.000446
+0.000442
+0.000446
+0.000431
+0.000430
+0.000431
+0.000444
+0.000431
+0.000418
+0.000439
+0.000430
+0.000433
+0.000427
+0.000447
+0.000459
+0.000430
+0.000438
+0.000432
+0.000429
+86.253278
+0.000443
+0.000427
+0.000430
+0.000429
+0.000428
+0.000433
+0.000423
+0.000392
+0.000584
+0.000434
+0.000436
+0.000448
+0.000414
+0.000440
+0.000443
+0.000407
+0.000421
+0.000450
+0.000441
+86.270061
+0.000442
+0.000438
+0.000447
+0.000433
+0.000440
+0.000420
+0.000448
+0.000442
+0.000445
+0.000430
+0.000430
+0.000448
+0.000437
+0.000428
+0.000443
+0.000435
+0.000436
+0.000447
+0.000432
+86.250279
+0.000457
+0.000437
+86.448833
+0.000407
+115.254519
+0.000438
+0.000429
+0.000419
+0.000422
+0.000422
+0.000450
+0.000433
+0.000441
+0.000426
+0.000428
+0.000427
+0.000394
+0.000418
+0.000428
+0.000423
+0.000426
+0.000405
+0.000409
+0.000415
+114.917270
+0.000438
+0.000420
+0.000418
+0.000425
+0.000432
+0.000419
+0.000435
+0.000381
+0.000445
+0.000441
+0.000428
+0.000426
+0.000428
+0.000428
+0.000445
+0.000425
+0.000423
+0.000430
+0.000422

reports/WeightFiltration/values.csv

@@ -0,0 +1,104 @@
+target_class, parameter_mia_accuracy, lookalike_accuracy, A-Dist, JS-Dist
+0,0.500000,0.477083, 0.093750, 0.531205
+1,0.500000,0.256250, 0.145833, 0.533884
+2,0.500000,0.335417, 0.177083, 0.563689
+3,0.500000,0.243750, 0.010417, 0.563501
+4,0.500000,0.189583, 0.031250, 0.568311
+5,0.500000,0.218750, 0.114583, 0.554095
+6,0.500000,0.327083, 0.072917, 0.528096
+7,0.500000,0.437500, 0.312500, 0.608898
+8,0.500000,0.287500, 0.229167, 0.537923
+9,0.500000,0.335417, 0.010417, 0.531386
+10,0.500000,0.127083, 0.177083, 0.488956
+11,0.500000,0.395833, 0.000000, 0.556688
+12,0.500000,0.208333, 0.041667, 0.515492
+13,0.500000,0.241667, 0.187500, 0.531538
+14,0.500000,0.304167, 0.114583, 0.546319
+15,0.500000,0.231250, 0.114583, 0.535395
+16,0.500000,0.206250, 0.072917, 0.551601
+17,0.500000,0.304167, 0.072917, 0.536588
+18,0.500000,0.375000, 0.104167, 0.528144
+19,0.500000,0.266667, 0.083333, 0.543631
+0,0.500000,0.418750, 0.031250, 0.535415
+1,0.500000,0.235417, 0.072917, 0.535499
+2,0.500000,0.329167, 0.291667, 0.563922
+3,0.500000,0.281250, 0.052083, 0.564283
+4,0.500000,0.204167, 0.260417, 0.573553
+5,0.500000,0.214583, 0.166667, 0.554907
+6,0.500000,0.304167, 0.020833, 0.530134
+7,0.500000,0.443750, 0.250000, 0.608279
+8,0.500000,0.343750, 0.156250, 0.533757
+9,0.500000,0.254167, 0.135417, 0.537570
+10,0.500000,0.122917, 0.156250, 0.487076
+11,0.500000,0.347917, 0.135417, 0.552417
+12,0.500000,0.225000, 0.145833, 0.519959
+13,0.500000,0.150000, 0.197917, 0.531879
+14,0.500000,0.264583, 0.041667, 0.544494
+15,0.500000,0.289583, 0.020833, 0.538959
+16,0.500000,0.266667, 0.031250, 0.554854
+17,0.500000,0.297917, 0.072917, 0.534680
+18,0.500000,0.327083, 0.156250, 0.528503
+19,0.500000,0.264583, 0.125000, 0.553348
+0,0.500000,0.468750, 0.041667, 0.540679
+1,0.500000,0.229167, 0.114583, 0.531994
+2,0.500000,0.320833, 0.125000, 0.561862
+3,0.500000,0.320833, 0.156250, 0.567223
+4,0.500000,0.160417, 0.302083, 0.570708
+5,0.500000,0.218750, 0.166667, 0.558651
+6,0.500000,0.270833, 0.010417, 0.526351
+7,0.500000,0.393750, 0.270833, 0.605921
+8,0.500000,0.308333, 0.083333, 0.534300
+9,0.500000,0.389583, 0.010417, 0.534346
+10,0.500000,0.170833, 0.291667, 0.490581
+11,0.500000,0.372917, 0.010417, 0.553222
+12,0.500000,0.181250, 0.145833, 0.521985
+13,0.500000,0.135417, 0.010417, 0.531411
+14,0.500000,0.310417, 0.041667, 0.549431
+15,0.500000,0.252083, 0.072917, 0.537570
+16,0.500000,0.237500, 0.000000, 0.550631
+17,0.500000,0.241667, 0.000000, 0.532652
+18,0.500000,0.335417, 0.114583, 0.530719
+19,0.500000,0.245833, 0.041667, 0.554328
+0,0.500000,0.443750, 0.072917, 0.538273
+1,0.500000,0.287500, 0.062500, 0.532444
+2,0.500000,0.400000, 0.250000, 0.565593
+3,0.500000,0.325000, 0.104167, 0.561017
+4,0.500000,0.252083, 0.125000, 0.574365
+5,0.500000,0.212500, 0.062500, 0.557207
+6,0.500000,0.377083, 0.041667, 0.532109
+7,0.500000,0.381250, 0.312500, 0.608354
+8,0.500000,0.300000, 0.125000, 0.530272
+9,0.500000,0.304167, 0.052083, 0.535231
+10,0.500000,0.152083, 0.166667, 0.486937
+11,0.500000,0.389583, 0.020833, 0.554443
+12,0.500000,0.237500, 0.010417, 0.515566
+13,0.500000,0.139583, 0.239583, 0.532841
+14,0.500000,0.250000, 0.114583, 0.545186
+15,0.500000,0.285417, 0.041667, 0.539053
+16,0.500000,0.364583, 0.052083, 0.557259
+17,0.500000,0.285417, 0.062500, 0.535905
+18,0.500000,0.420833, 0.291667, 0.530528
+19,0.500000,0.235417, 0.041667, 0.550465
+0,0.500000,0.420833, 0.020833, 0.536924
+1,0.500000,0.289583, 0.114583, 0.535009
+2,0.500000,0.364583, 0.208333, 0.561020
+3,0.500000,0.312500, 0.000000, 0.563347
+4,0.500000,0.241667, 0.135417, 0.568564
+5,0.500000,0.227083, 0.229167, 0.554962
+6,0.500000,0.329167, 0.072917, 0.528871
+7,0.500000,0.404167, 0.177083, 0.608461
+8,0.500000,0.312500, 0.114583, 0.533693
+9,0.500000,0.300000, 0.052083, 0.534936
+10,0.500000,0.143750, 0.031250, 0.488405
+11,0.500000,0.350000, 0.052083, 0.552083
+12,0.500000,0.239583, 0.062500, 0.518281
+13,0.500000,0.133333, 0.135417, 0.536575
+14,0.500000,0.254167, 0.052083, 0.547499
+15,0.500000,0.222917, 0.145833, 0.538462
+16,0.500000,0.270833, 0.052083, 0.553830
+17,0.500000,0.277083, 0.052083, 0.533158
+18,0.500000,0.427083, 0.239583, 0.525671
+19,0.500000,0.279167, 0.020833, 0.546591
+0,0.500000,0.441667, 0.072917, 0.536959
+1,0.500000,0.204167, 0.000000, 0.535119
+2,0.500000,0.302083, 0.041667, 0.562120