> For the complete documentation index, see [llms.txt](https://help.protecto.ai/tokenization-packages/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.protecto.ai/tokenization-packages/protecto-tokenization/unmask-a-token.md).

# Unmask a Token

In tokenization, unmasking is the procedure of reversing the masking process to recover the original sensitive data from its masked representation.

* The ProtectoVault object is instantiated with your tokenization key.
* The input needs to consist of a list of masked text.
* The `unmask` method is then used to retrieve the original data from the previously masked result.

*<mark style="color:orange;">Let's take an example. If "George Williams" is masked as "wRePE302Qx vUc7DruuWm," and the user provides the second masked input, "vUc7DruuWm," the unmasked output should be "Williams."</mark>*

The user can also submit a list of masked inputs, such as \<masked value1>,\<masked value2> etc to obtain the respective unmasked values.

Learn more by checking out the section on [Supporting Token and Format Types.](/tokenization-packages/protecto-tokenization/supporting-token-and-format-types.md)

***Note:*** \
To obtain the `<auth token>`, please refer to the [Step-by-Step Guide to Obtain Your Auth Token](/tokenization-packages/protecto-tokenization/step-by-step-guide-to-obtain-your-auth-token.md)

Eg :

*Code Snippet*

```python
# Import the ProtectoVault class from the protecto_ai module
from protecto_ai import ProtectoVault
# Create an instance of ProtectoVault with your authentication token
obj = ProtectoVault("<auth_token>")
# Use the unmask method to retrieve the actual data.
result = obj.unmask(["<PER>wRePE302Qx vUc7DruuWm</PER> is happy"])
# Print the unmasked result
print(result)
```

Result:

```python
{ 
  "data": [ 
    { 
      "token_value": "<PER>wRePE302Qx vUc7DruuWm</PER> is happy", 
      "value": "George Washington is happy" 
    } 
  ], 
  "success": true, 
  "error": { 
    "message": "" 
  } 
} 
```

For more comprehensive information about our product, kindly reach out to us through our website at <https://www.protecto.ai/>.