# US 2025/0097226 A1 · Detecting data exfiltration via api calls using language model embeddings

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0097226 A1
- Document ID: US20250097226A1
- Status: Published application
- Kind: A1
- Application number: 18/368,873
- Filed: 2023-09-15
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Charles Fleming; Jayanth SRINIVASA; Ramana Rao V.R. KOMPELLA
- Web page: https://patentgrep.com/patent/US20250097226A1

## CPC

- H04L 63/10: {for controlling access to devices or network resources}
- G06F 9/541: {via adapters, e.g. between incompatible applications}
- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- G06F 40/30: Semantic analysis
- G06N 20/00: Machine learning
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 2209/542: Intercept
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In one implementation, a device intercepts return data for an application programming interface call to be sent to a requester via a network. The device converts the return data into an embedding. The device determines a similarity between the embedding and one or more embeddings in a database that were generated from one or more documents deemed sensitive. The device blocks, based on the similarity, the return data from being sent via the network to the requester.

## Claims

### Claim 1

A method comprising:
intercepting, by a device, return data for an application programming interface call to be sent to a requester via a network;
converting, by the device, the return data into an embedding;
determining, by the device, a similarity between the embedding and one or more embeddings in a database that were generated from one or more documents deemed sensitive; and
blocking, by the device and based on the similarity, the return data from being sent via the network to the requester.

### Claim 2 (depends on 1)

The method as in claim 1, wherein the device is located in a service mesh.

### Claim 3 (depends on 1)

The method as in claim 1, wherein the return data is intercepted by a sidecar proxy associated with a service or microservice that receives the application programming interface call.

### Claim 4 (depends on 3)

The method as in claim 3, wherein blocking the return data from being sent via the network to the requester comprises:
sending a notification to the sidecar proxy indicative to block the return data from being sent.

### Claim 5 (depends on 1)

The method as in claim 1, wherein converting the return data into the embedding by:
inputting the return data into an artificial intelligence-based language model trained to convert text into embeddings.

### Claim 6 (depends on 5)

The method as in claim 5, further comprising:
generating, by the device and using the artificial intelligence-based language model, the one or more embeddings from the one or more documents deemed sensitive; and
storing the one or more embeddings in the database.

### Claim 7 (depends on 1)

The method as in claim 1, wherein the one or more documents were flagged as sensitive via a user interface.

### Claim 8 (depends on 1)

The method as in claim 1, wherein the database is a vector database.

### Claim 9 (depends on 1)

The method as in claim 1, wherein the one or more documents include personally identifiable information.

### Claim 10 (depends on 1)

The method as in claim 1, wherein the similarity comprises a Euclidean distance or cosine similarity.

### Claim 11

An apparatus, comprising:
one or more network interfaces;
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and
a memory configured to store a process that is executable by the processor, the process when executed configured to:
intercept a return data for an application programming interface call to be sent to a requester via a network;
convert the return data into an embedding;
determine a similarity between the embedding and one or more embeddings in a database that were generated from one or more documents deemed sensitive; and
block, based on the similarity, the return data from being sent via the network to the requester.

### Claim 12 (depends on 11)

The apparatus as in claim 11, wherein the apparatus is located in a service mesh.

### Claim 13 (depends on 11)

The apparatus as in claim 11, wherein the return data is intercepted by a sidecar proxy associated with a service or microservice that receives the application programming interface call.

### Claim 14 (depends on 13)

The apparatus as in claim 13, wherein the apparatus blocks the return data from being sent via the network to the requester by:
sending a notification to the sidecar proxy indicative to block the return data from being sent.

### Claim 15 (depends on 11)

The apparatus as in claim 11, wherein the apparatus converts the return data into the embedding by:
inputting the return data into an artificial intelligence-based language model trained to convert text into embeddings.

### Claim 16 (depends on 15)

The apparatus as in claim 15, wherein the process when executed is further configured to:
generate, using the artificial intelligence-based language model, the one or more embeddings from the one or more documents deemed sensitive; and
store the one or more embeddings in the database.

### Claim 17 (depends on 11)

The apparatus as in claim 11, wherein the one or more documents were flagged as sensitive via a user interface.

### Claim 18 (depends on 11)

The apparatus as in claim 11, wherein the database is a vector database.

### Claim 19 (depends on 11)

The apparatus as in claim 11, wherein the one or more documents include personally identifiable information.

### Claim 20

A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
intercepting, by the device, return data for an application programming interface call to be sent to a requester via a network;
converting, by the device, the return data into an embedding;
determining, by the device, a similarity between the embedding and one or more embeddings in a database that were generated from one or more documents deemed sensitive; and
blocking, by the device and based on the similarity, the return data from being sent via the network to the requester.
