# US 2021/0334646 A1 · Robustness-aware quantization for neural networks against weight perturbations

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

- Number: US 2021/0334646 A1
- Document ID: US20210334646A1
- Status: Published application
- Kind: A1
- Application number: 16/861,019
- Filed: 2020-04-28
- Published: 2021-10-28
- Earliest claimed: 2020-04-28
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Sijia Liu; Pin-Yu Chen; Gaoyuan Zhang; Chuang Gan
- Web page: https://patentgrep.com/patent/US20210334646A1

## CPC

- G06N 3/08: Learning methods
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/09: Supervised learning
- G06N 3/094: Adversarial learning
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method of utilizing a computing device to optimize weights within a neural network to avoid adversarial attacks includes receiving, by a computing device, a neural network for optimization. The method further includes determining, by the computing device, on a region by region basis one or more robustness bounds for weights within the neural network. The robustness bounds indicating values beyond which the neural network generates an erroneous output upon performing an adversarial attack on the neural network. The computing device further averages all robustness bounds on the region by region basis. The computing device additionally optimizes weights for adversarial proofing the neural network based at least in part on the averaged robustness bounds.

## Claims

### Claim 1

A method of utilizing a computing device to optimize weights within a neural network to avoid adversarial attacks, the method comprising:
receiving, by a computing device, a neural network for optimization;
determining, by the computing device, on a region by region basis one or more robustness bounds for weights within the neural network, the robustness bounds indicating values beyond which the neural network generates an erroneous output upon performing an adversarial attack on the neural network;
averaging, by the computing device, all robustness bounds on the region by region basis; and
optimizing, by the computing device, weights for adversarial proofing the neural network based at least in part on the averaged robustness bounds.

### Claim 2 (depends on 1)

The method of claim 1, wherein the robustness bounds comprise a certified weight perturbation region such that the neural network maintains a prediction accuracy upon weight parameter perturbation occurring within the certified weight perturbation region.

### Claim 3 (depends on 1)

The method of claim 1, wherein averaging further comprising:
determining, by the computing device, a certified weight perturbation region for multiple inputs such that the neural network maintains a prediction accuracy upon weight parameter perturbation occurring within the certified weight perturbation region.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining, by the computing device, a maximum perturbation radius such that an optimal objective value is positive.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
applying, by the computing device, certificate-aware weight perturbation constraints based on the averaged robustness bounds in quantization design of the neural network.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
training, by the computing device, the neural network using alternating direction method of multipliers (ADMM) and incorporating the certificate-aware weight perturbation constraints,
wherein the neural network is a quantized deep neural network.

### Claim 7 (depends on 5)

The method of claim 5, further comprising:
discretizing, by the computing device, model weights for the neural network based on a finite number of bits while preserving the machine learning model output prediction accuracy.

### Claim 8 (depends on 7)

The method of claim 7, further comprising:
propagating, by the computing device, the averaged robustness bounds throughout a plurality of neurons in the neural network.

### Claim 9

A computer program product for optimizing weights within a neural network to avoid adversarial attacks, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
receive, by the processor, a neural network for optimization;
determine, by the processor, on a region by region basis one or more robustness bounds for weights within the neural network, the robustness bounds indicating values beyond which the neural network generates an erroneous output upon performing an adversarial attack on the neural network;
average, by the processor, all robustness bounds on the region by region basis; and
optimize, by the processor, weights for adversarial proofing the neural network based at least in part on the averaged robustness bounds.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the robustness bounds comprise a certified weight perturbation region such that the neural network maintains a prediction accuracy upon weight parameter perturbation occurring within the certified weight perturbation region.

### Claim 11 (depends on 9)

The computer program product of claim 9, wherein averaging further comprising:
determine, by the processor, a certified weight perturbation region for multiple inputs such that the neural network maintains a prediction accuracy upon weight parameter perturbation occurring within the certified weight perturbation region.

### Claim 12 (depends on 9)

The computer program product of claim 9, wherein the program instructions executable by the processor further cause the processor to:
determine, by the processor, a maximum perturbation radius such that an optimal objective value is positive.

### Claim 13 (depends on 9)

The computer program product of claim 9, wherein the program instructions executable by the processor further cause the processor to:
apply, by the processor, certificate-aware weight perturbation constraints based on the averaged robustness bounds in quantization design of the neural network.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein the program instructions executable by the processor further cause the processor to:
train, by the processor, the neural network using alternating direction method of multipliers (ADMM) and incorporating the certificate-aware weight perturbation constraints, wherein the neural network is a quantized deep neural network.

### Claim 15 (depends on 13)

The computer program product of claim 13, wherein the program instructions executable by the processor further cause the processor to:
discretize, by the processor, model weights for the neural network based on a finite number of bits while preserving the machine learning model output prediction accuracy; and
propagate, by the processor, the averaged robustness bounds throughout a plurality of neurons in the neural network.

### Claim 16

An apparatus comprising:
a memory configured to store instructions; and
a processor configured to execute the instructions to:
receive a neural network for optimization;
determine on a region by region basis one or more robustness bounds for weights within the neural network, the robustness bounds indicating values beyond which the neural network generates an erroneous output upon performing an adversarial attack on the neural network;
average all robustness bounds on the region by region basis; and
optimize weights for adversarial proofing the neural network based at least in part on the averaged robustness bounds.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein:
the robustness bounds comprise a certified weight perturbation region such that the neural network maintains a prediction accuracy upon weight parameter perturbation occurring within the certified weight perturbation region; and
average all of the robustness bounds further comprising:
determining a certified weight perturbation region for multiple inputs such that the neural network maintains a prediction accuracy upon weight parameter perturbation occurring within the certified weight perturbation region.

### Claim 18 (depends on 16)

The apparatus of claim 16, wherein the processor is further configured to execute the instructions to:
determine a maximum perturbation radius such that an optimal objective value is positive; and
apply certificate-aware weight perturbation constraints based on the averaged robustness bounds in quantization design of the neural network.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein the processor is further configured to execute the instructions to:
train the neural network using alternating direction method of multipliers (ADMM) and incorporating the certificate-aware weight perturbation constraints,
wherein the neural network is a quantized deep neural network.

### Claim 20 (depends on 18)

The apparatus of claim 18, wherein the processor is further configured to execute the instructions to:
discretize model weights for the neural network based on a finite number of bits while preserving the machine learning model output prediction accuracy; and
propagate the averaged robustness bounds throughout a plurality of neurons in the neural network.
