Platform For AI:LLM-Sensitive Content Mask (DLC)

Supported computing resources

Deep Learning Containers (DLC)

Algorithm description

The LLM-Sensitive Content Mask (DLC) component masks the following sensitive information:

• Mobile phone numbers: Strings that match the following regular expressions are replaced with [MOBILEPHONE].

  • r'(?<!\d)(1(3[0-9]|4[579]|5[0-3,5-9]|6[6]|7[0135678]|8[0-9]|9[89])\d{8})(?!\d)'

  • r'(?<!\d)(1[\d]{2}-\d{4}-\d{4}\D|\D1\d{10}\D|\D1[\d]{2} \d{4} \d{4})(?!\d)'

  • r'(?<!\d)(1[3-9]\d{9})(?!\d)'

• Landline phone numbers: Strings that match the following regular expression are replaced with [TELEPHONE].

  • r'(?<!\d)(\(?0\d{2,3}[-\s)]?\d{7,8})(?!\d)'

• Email addresses: Strings that match the following regular expression are replaced with [EMAIL].

  • r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+.[a-zA-Z0-9-.]+'

• People's Republic of China (PRC) resident identity card numbers: Strings that match the following regular expressions are replaced with [IDNUM].

  • r'(?<!\d)([1-6]\d{5}[12]\d{3}(0[1-9]|1[12])(0[1-9]|1[0-9]|2[0-9]|3[01])\d{3}(\d|X|x))(?!\d)'

  • r'(?<!\d)([1-9]\d{5}[12]\d{3}(0[1-9]|1[012])(0[1-9]|[12][0-9]|3[01])\d{3}[0-9xX])(?!\d)'

The following example shows how an email address is masked:

Configure the component

On the pipeline page of Machine Learning Designer, configure the parameters of the LLM-Sensitive Content Mask (DLC) component.