# US 2026/0065130 A1 · Bi-directional low-rank adaptation for machine unlearning and information retention

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

- Number: US 2026/0065130 A1
- Document ID: US20260065130A1
- Status: Published application
- Kind: A1
- Application number: 18/821,116
- Filed: 2024-08-30
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Yihua Zhang; Yuguang Yao; Gaowen Liu; Ramana Rao V.R. Kompella
- Web page: https://patentgrep.com/patent/US20260065130A1

## CPC

- G06N 20/00: Machine learning
- G06N 3/045: Combinations of networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In one implementation, a device may identify specific knowledge to be unlearned in a machine learning model. The device may identify layers of the machine learning model that are responsible for the specific knowledge to be unlearned. The device may apply a low rank adaptation unlearning component to each of the layers of the machine learning model that are responsible for the specific knowledge to be unlearned. The device may apply a low rank adaptation retention component to layers of the machine learning model that are not responsible for the specific knowledge to be unlearned.

## Claims

### Claim 1

A method, comprising:
identifying, by a device, specific knowledge to be unlearned in a machine learning model;
identifying, by a device, layers of the machine learning model that are responsible for the specific knowledge to be unlearned;
applying, by the device, a low rank adaptation unlearning component to each of the layers of the machine learning model that are responsible for the specific knowledge to be unlearned; and
applying, by the device, a low rank adaptation retention component to layers of the machine learning model that are not responsible for the specific knowledge to be unlearned.

### Claim 2 (depends on 1)

The method as in claim 1, wherein the low rank adaptation unlearning component and the low rank adaptation retention component are applied to the machine learning model in a bi-directional manner to respectively perform knowledge unlearning and knowledge retention tasks to the machine learning model.

### Claim 3 (depends on 1)

The method as in claim 1, wherein the machine learning model is one or more of a vision transformer model, a language model, or a text-to-image model.

### Claim 4 (depends on 1)

The method as in claim 1, further comprising:
performing a layer attribution operation to the machine learning model.

### Claim 5 (depends on 4)

The method as in claim 4, wherein the layer attribution operation includes determining a sensitivity of each of the layers of the machine learning model to inputs associated with the specific knowledge to be unlearned.

### Claim 6 (depends on 4)

The method as in claim 4, wherein the layers of the machine learning model that are responsible for the specific knowledge to be unlearned are identified based on the layer attribution operation.

### Claim 7 (depends on 1)

The method as in claim 1, wherein the layers of the machine learning model that are responsible for the specific knowledge to be unlearned are identified based at least in part on manual layer selections by a user.

### Claim 8 (depends on 1)

The method as in claim 1, further comprising:
configuring a complexity of the low rank adaptation unlearning component based on a user specification of a targeted rank for the low rank adaptation unlearning component.

### Claim 9 (depends on 1)

The method as in claim 1, further comprising:
configuring an intensity of unlearning of the specific knowledge by the low rank adaptation unlearning component based on a user specification of an unlearning strength for the low rank adaptation unlearning component.

### Claim 10 (depends on 1)

The method as in claim 1, further comprising:
reversing application of the low rank adaptation unlearning component to the machine learning model responsive to a reversal indication by a user.

### 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:
identify specific knowledge to be unlearned in a machine learning model;
identify layers of the machine learning model that are responsible for the specific knowledge to be unlearned;
apply a low rank adaptation unlearning component to each of the layers of the machine learning model that are responsible for the specific knowledge to be unlearned; and
apply a low rank adaptation retention component to layers of the machine learning model that are not responsible for the specific knowledge to be unlearned.

### Claim 12 (depends on 11)

The apparatus as in claim 11, wherein the low rank adaptation unlearning component and the low rank adaptation retention component are applied to the machine learning model in a bi-directional manner to respectively perform knowledge unlearning and knowledge retention tasks to the machine learning model.

### Claim 13 (depends on 11)

The apparatus as in claim 11, wherein the machine learning model is one or more of a vision transformer model, a language model, or a text-to-image model.

### Claim 14 (depends on 11)

The apparatus as in claim 11, wherein the process is further configured to:
perform a layer attribution operation to the machine learning model based on the specific knowledge to be unlearned.

### Claim 15 (depends on 14)

The apparatus as in claim 14, wherein the layer attribution operation includes determining a sensitivity of each of the layers of the machine learning model to inputs associated with the specific knowledge to be unlearned.

### Claim 16 (depends on 14)

The apparatus as in claim 14, wherein the layers of the machine learning model that are responsible for the specific knowledge to be unlearned are identified based on the layer attribution operation.

### Claim 17 (depends on 11)

The apparatus as in claim 11, wherein the layers of the machine learning model that are responsible for the specific knowledge to be unlearned are identified based at least in part on manual layer selections by a user.

### Claim 18 (depends on 11)

The apparatus as in claim 11, wherein the process is further configured to:
configure a complexity of the low rank adaptation unlearning component based on a user specification of a targeted rank for the low rank adaptation unlearning component.

### Claim 19 (depends on 11)

The apparatus as in claim 11, wherein the process is further configured to:
configure an intensity of unlearning of the specific knowledge by the low rank adaptation unlearning component based on a user specification of an unlearning strength for the low rank adaptation unlearning component.

### Claim 20

A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
identifying specific knowledge to be unlearned in a machine learning model;
identifying layers of the machine learning model that are responsible for the specific knowledge to be unlearned;
applying a low rank adaptation unlearning component to each of the layers of the machine learning model that are responsible for the specific knowledge to be unlearned; and
applying a low rank adaptation retention component to layers of the machine learning model that are not responsible for the specific knowledge to be unlearned.
