Dynamic risk detection and mitigation of compromised customer log-in credentials

1. A method for preemptively reducing the risk of compromising the login credentials of a Customer Cn, comprising the steps of:

(A) continuously searching data elements in at least one website of a dark web and at least one website of one of a deep web and a surface web or both of the deep web and the surface web, for information associated with said login credential,

wherein said searching of data elements in the deep web is based, at least in part, on the information from the dark web,

wherein searching the data elements in a surface web are based, at least in part, on the data elements' information from the dark web and/or the deep web, and

wherein said dark web is accessible over an anonymous network;

(B) incorporating the unique authentication and access controls of the Service Provider with the information in Step A;

(C) determining a dynamic Risk Score for said login credential of said Customer Cn using the formula:

R ( C n ,SPi, t )= f{X 1 , X 2 , X 3 . . . }

wherein the dynamic Risk Score R is specific to a Customer Cn, at a specific Service Provider SPi, and at a given time t;

wherein said dynamic Risk Score is a function of Xs, wherein said Xs are data elements;

wherein said dynamic Risk Score is calculated using multivariate machine-learning models such that they intelligently analyze said data elements Xs and provide said dynamic Risk Score;

wherein said dynamic Risk Score, as it relates to said specific Service Provider SPi, is dynamically communicated to said specific Service Provider SPi prior to a transaction request, and not after said transaction request using an application programming interface (API);

(D) comparing said dynamic Risk Score, dynamically or periodically with a pre-determined threshold Risk Score; and taking one of the following steps:

(D1) modifying an authentication requirement for the Customer and seeking said authentication from the Customer, wherein said authentication requirement is a function of the breach of said pre-determined threshold Risk Score;

(D2) modifying an authentication requirement for the Customer, while temporarily suspending services to said Customer credential, pre-emptively notifying the Customer of said suspension, seeking said authentication from said Customer, and restarting or shutting down services connected to said Customer credentials.

2. The method as recited in claim 1 , wherein modifying the authentication requirement comprises identifying an enhanced security protocol to authenticate the User.

3. The method as recited in claim 2 , wherein the enhanced security protocol comprises a multi-factor authentication of the User.

4. The method as recited in claim 1 , wherein the data elements comprise one of dynamic content, multimedia content, audio content, and a picture.

5. The method of claim 1 , wherein the data elements are searched using configurable search parameters.

6. The method of claim 1 , wherein the anonymous network comprises a Tor server.

7. A computer program product comprising:

a non-transitory computer readable storage medium comprising computer readable program code embodied therewith, the computer readable program code comprising:

(A) computer readable program code configured to continuously receive information obtained from searching data elements in at least one website of a dark web and at least one website of one of a deep web and a surface web or both of the deep web and the surface web, for information associated with a login credential,

wherein said searching of data elements in the deep web is based, at least in part, on the information from the dark web,

wherein searching the data elements in a surface web are based, at least in part, on the data elements' information from the dark web and/or the deep web, and

wherein said dark web is accessible over an anonymous network;

(B) computer readable program code configured to dynamically incorporate the unique authentication and access controls of the Service Provider with the information in computer readable program code in (A);

(C) computer readable program code configured to determine a dynamic Risk Score for said login credential of said Customer Cn using the formula:

R ( C n ,SP i , t )= f{X 1 , X 2 , X 3}

wherein the dynamic Risk Score R is specific to a Customer Cn, at a specific Service Provider SPi, and at a given time t,

wherein said dynamic Risk Score is a function of Xs, wherein said Xs are data elements,

wherein said dynamic Risk Score is calculated using multivariate machine-learning models such that they intelligently analyze said data elements Xs and provide said dynamic Risk Score; a risk score, at least in part, on the information associated with a User login credentials;

(D) computer readable program code configured to compare said dynamic Risk Score, dynamically or periodically with a pre-determined threshold Risk Score;

(E) computer readable program code configured to modify an authentication requirement for the Customer and seeking said authentication from the Customer, wherein said authentication requirement is a function of the breach of said pre-determined threshold Risk Score; and

(F) computer readable program code configured to modify an authentication requirement for the Customer, while temporarily suspending services to said Customer credential, pre-emptively notifying the Customer of said suspension, seeking said authentication from said Customer, and restarting or shutting down services connected to said Customer credentials.

8. The computer program product of claim 7 , wherein the information is related to one of a hacker forum, a dark web uniform resource locator (URL), and the User login credential.

9. A system comprising:

(A) a data processor configured to execute a first set of instructions to: continuously search data elements in at least one website of a dark web and at least one website of one of a deep web and a surface web or both of the deep web and the surface web, for information associated with said login credential, wherein said searching of data elements in the deep web is based, at least in part, on the information from the dark web,

wherein searching the data elements in a surface web are based, at least in part, on the data elements' information from the dark web and/or the deep web, and

wherein said dark web is accessible over an anonymous network;

(B) a system configured to incorporate the unique authentication and access controls of the Service Provider with the information in System A;

(C) a Credential Risk Scoring Engine processor configured to determine a dynamic Risk Score for said login credential of said Customer Cn using the formula:

R ( C n ,SP i , t )= f{X 1 , X 2 , X 3}

wherein the dynamic Risk Score R is specific to a Customer Cn, at a specific Service Provider SPi, and at a given time t;

wherein said dynamic Risk Score is a function of Xs, wherein said Xs are data elements;

wherein said dynamic Risk Score is calculated using multivariate machine-learning models such that they intelligently analyze said data elements Xs and provide said dynamic Risk Score;

wherein said dynamic Risk Score, as it relates to said specific Service Provider SPi, is dynamically communicated to said specific Service Provider SPi prior to a transaction request, and not after said transaction request using an application programming interface (API);

(D) a data processor to compare said dynamic Risk Score in (C), dynamically or periodically, with a pre-determined threshold Risk Score;

(E) a system configured to modify an authentication requirement for the Customer and seeking said authentication from the Customer, wherein said authentication requirement is a function of the breach of said pre-determined threshold Risk Score; and

(F) a system configured to modify an authentication requirement for the Customer, while temporarily suspending services to said Customer credential, pre-emptively notifying the Customer of said suspension, seeking said authentication from said Customer, and restarting or shutting down services connected to said Customer credentials.

10. The method as recited in claim 1 , further comprising: generating a machine learning model with feedback from the Service Provider on the accuracy of the previous score.