Frequency-Domain Image Filtering Against Adversarial Perturbations

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Deep neural networks are susceptible to adversarial perturbations, which are imperceptible manipulations that can significantly affect their output, and existing defense mechanisms are computationally complex, do not scale well, and do not improve comprehensibility, posing challenges for robustness and efficient deployment in real-world applications.

Innovation Solution

Applying a Wiener filter in the frequency domain to suppress adversarial perturbations by recognizing their characteristic patterns, which are visible in the frequency domain, thereby enhancing the robustness of neural networks without significant computational overhead.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If deep neural networks are trained using purely data-driven parameter fitting without expert intervention, then the training process is simplified and automation is improved, but the network becomes susceptible to adversarial perturbations and loses robustness

Engineering Contradiction:
Improvetraining automationVSAvoidrobustness against adversarial perturbations
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The patent applies preliminary action by introducing a denoising autoencoder before the main neural network processing. This autoencoder is trained in advance to recognize and remove adversarial perturbations from input images before they reach the classification network, thereby preventing the network from being fooled by adversarial examples while maintaining the data-driven training approach

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The denoising autoencoder serves as an intermediary component between the input image and the classification network. It acts as a mediator that cleans the input data by removing adversarial perturbations, allowing the main network to process only clean, legitimate image data without being exposed to harmful adversarial examples

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If adversarial training is performed to improve robustness, then reliability against adversarial attacks is improved, but device complexity and computational overhead increase

Engineering Contradiction:
Improverobustness against adversarial attacksVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the robustness problem into two independent components: a denoising autoencoder for removing perturbations and a main classification network for processing clean data. This segmentation allows each component to be optimized separately, reducing the overall complexity compared to redesigning the entire network for adversarial robustness

Inventive Principle:
Principle #1Segmentation

3Reliability

If post-processing methods are applied to ensure stability and robustness, then reliability is improved, but processing time and productivity are reduced

Engineering Contradiction:
Improvestability and robustnessVSAvoidprocessing speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The denoising autoencoder is integrated as a continuous preprocessing step that operates in real-time alongside the main network inference. This continuous action ensures that robustness is maintained without requiring separate post-processing steps, thereby minimizing additional processing time and maintaining high productivity

Inventive Principle:
Principle #20Continuity of useful action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The proposed method effectively suppresses adversarial perturbations across various attacks, maintaining performance on clean images and reducing latency, thus improving the robustness and efficiency of neural networks in real-world applications.

Implementation Method 1

The filter is configured to suppress adversarial perturbations within the image data by identifying and filtering out specific frequency patterns in the frequency domain

Methodology Applied
Scientific EffectFourier transform:

Implementation Method 2

applying a filter on the image data to generate filtered image data... The filter is configured to suppress adversarial perturbations within the image data

Methodology Applied
Scientific EffectFrequency domain filtering: Filter (optical)

Data Source

PatentEP3979187B1Methods, systems and computer programs for processing image data and for generating a filter
Publication Date: 2026.05.20 VOLKSWAGEN AG
  • EP3979187B1 patent drawingFigure 1a~1b
  • EP3979187B1 patent drawingFigure 1c
  • EP3979187B1 patent drawingFigure 2a~2b

AI summary

Various aspects of the present disclosure relate to a method, system and computer program for processing image data, to a vehicle comprising such a system, and to a method, system and computer program for generating a filter. The method for processing image data comprises obtaining (110) the image data. The method comprises applying (120) a filter on the image data to generate filtered image data, the filter being configured to suppress adversarial perturbations within the image data. The method comprises processing (130) the filtered image data using a machine-learning model.