SENSITIVE DATA PROTECTION USING AN AUXILIARY MACHINE-LEARNING TOOL
Methods and apparatus are disclosed for providing security for a target machine-learning (ML) tool and its host system. Input data is fed in parallel to a second ML tool. Fingerprints of the second ML tool are used to monitor changes in the second tool. Fingerprint changes above a threshold indicate anomalous input data and warn of possible threat to the target tool. Anomaly detection enables diagnosis and remediation. Compact fingerprints are easy to handle, and hide details of the underlying tool. Concurrently, fingerprints are large enough to be sensitive to localized variations within the tool. Alternative embodiments monitor fingerprints of the target tool itself. Further embodiments monitor input or output data streams for sensitive data using a trained ML classifier. Variations and applications are disclosed.
1 . A computer-implemented method of monitoring output of a first machine-learning (ML) tool, comprising:
at training time:
(a) training a second machine-learning (ML) tool to learn language or domain knowledge; and
(b) training the second ML tool to classify inputted data based on sensitivity; and
at inference time:
(c) inputting, to the second ML tool, groups of input data based on output generated by the first ML tool;
(d) receiving, from the second ML tool, respective classifications of each group of input data;
for a first group having a classification indicating that the respective input data is sensitive:
(e) flagging, discarding, or redacting at least a portion of the sensitive input data; and
for a second group having a classification indicating that the respective input data is not sensitive:
(f) forwarding the second group to a destination.
2 . The computer-implemented method of claim 1 , wherein act (b) is performed using training data labeled based on the sensitivity.
3 . The computer-implemented method of claim 1 , further comprising:
using the first group for fine-tuning the first ML tool.
4 . The computer-implemented method of claim 1 , wherein the first ML tool or the second ML tool is part of a microservice in a network of microservices configured as a copilot.
5 . The computer-implemented method of claim 4 , wherein the first ML tool is part of a core microservice of the copilot.
6 . The computer-implemented method of claim 4 , wherein the first ML tool is part of a data producer or a retrieval microservice of the copilot.
7 . The computer-implemented method of claim 4 , wherein the second group is forwarded at act (f) toward a client of the copilot.
8 . One or more computer-readable media storing instructions which, when executed on one or more hardware processors, cause the one or more hardware processors to perform operations comprising:
at training time:
(a) training a second machine-learning (ML) tool to learn language or domain knowledge; and
(b) training the second ML tool to classify inputted data based on sensitivity; and
at inference time:
(c) inputting, to the second ML tool, groups of input data based on output generated by the first ML tool;
(d) receiving, from the second ML tool, respective classifications of each group of input data;
for a first group having a classification indicating that the respective input data is sensitive:
(e) flagging, discarding, or redacting at least a portion of the sensitive input data; and
for a second group having a classification indicating that the respective input data is not sensitive:
(f) forwarding the second group to a destination.
9 . The one or more computer-readable media of claim 8 , wherein operation (b) is performed using training data labeled based on the sensitivity.
10 . The one or more computer-readable media of claim 8 , wherein the operations further comprise:
using the first group for fine-tuning the first ML tool.
11 . The one or more computer-readable media of claim 8 , wherein the first ML tool or the second ML tool is part of a microservice in a network of microservices configured as a copilot.
12 . The one or more computer-readable media of claim 11 , wherein the first ML tool is part of a core microservice of the copilot.
13 . The one or more computer-readable media of claim 11 , wherein the first ML tool is part of a data producer or a retrieval microservice of the copilot.
14 . A system, comprising:
one or more hardware processors with memory coupled thereto; and
computer-readable media storing instructions which, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations comprising:
at training time:
(a) training a second machine-learning (ML) tool to learn language or domain knowledge; and
(b) training the second ML tool to classify inputted data based on sensitivity; and
at inference time:
(c) inputting, to the second ML tool, groups of input data based on output generated by the first ML tool;
(d) receiving, from the second ML tool, respective classifications of each group of input data;
for a first group having a classification indicating that the respective input data is sensitive:
(e) flagging, discarding, or redacting at least a portion of the sensitive input data; and
for a second group having a classification indicating that the respective input data is not sensitive:
(f) forwarding the second group to a destination.
15 . The system of claim 14 , wherein operation (b) is performed using training data labeled based on the sensitivity.
16 . The system of claim 14 , wherein the operations further comprise:
using the first group for fine-tuning the first ML tool.
17 . The system of claim 14 , wherein the first ML tool or the second ML tool is part of a microservice in a network of microservices configured as a copilot.
18 . The system of claim 17 , wherein the first ML tool is part of a core microservice of the copilot.
19 . The system of claim 17 , wherein the first ML tool is part of a data producer or a retrieval microservice of the copilot.
20 . The one or more computer-readable media of claim 17 , wherein the second group is forwarded at operation (f) toward a client of the copilot.