It seems like the 'success' value in the return of the 'attack' function is overconfident.

It seems like the 'success' value in the return of the 'attack' function is overconfident.
```python
if __name__ == '__main__':
args = parser.parse_args()
model = ModelController(args).get_model().eval()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
ConvCTrainer.load_model(args, model, device)

data_controller = DataCController(args)
eval_loader = data_controller.get_test_dataloader()
mean, std = data_controller.aug_controller.get_normalize_param()

attack = LinfFastGradientAttack()

fmodel = PyTorchModel(model, bounds = (0, 1), preprocessing = dict(mean = mean, std = std))

epsilons = [0.01, 0.03, 0.1, 0.3, 0.5]
cnt, total = torch.zeros(len(epsilons)).to(device),\
torch.zeros(len(epsilons)).to(device)

correct = torch.zeros(len(epsilons)).to(device)

for _, (images, labels) in enumerate(eval_loader):
images = images.to(device)
labels = labels.to(device)

images = images * std[:, None, None] + mean[:, None, None]

_, advs_list, success = attack(fmodel, images, labels, epsilons = epsilons)
cnt += success.sum(axis = 1)
total += images.shape[0]

for i, advs in enumerate(advs_list):
preds = model(advs).argmax(dim=1)
correct[i] += (preds == labels).sum().item() # Compute accuracy for each epsilon

print(f"Success rate vector: {cnt / total}")
print(f"Accuracy vector for each epsilon: {correct / total}")
```

And the output of this code is
```shell
Success rate vector: tensor([0.3397, 0.4297, 0.5650, 0.6253, 0.6954], device='cuda:0')
Accuracy vector for each epsilon: tensor([0.9872, 0.9851, 0.9676, 0.7457, 0.3955], device='cuda:0')
```

Start at the LinfFastGradientAttack call and its success return, then compare that value with the model predictions computed for each advs in the example. Reproduce the reported success-rate and accuracy vectors with the shown PyTorch evaluation code; done means the returned success values agree with the attack outcome represented by those predictions.

Written by the indexing model from the issue text.