Model-Agnostic Adversarial Attack Detection for AI Object Detectors

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for detecting adversarial attacks on AI-based object detectors require access to the model or image inputs, making them model-dependent and less effective for real-time applications, especially in scenarios like smart traffic systems where accuracy and reliability are critical.

Innovation Solution

A model-agnostic, real-time detection system using the Isolation Forest algorithm that identifies adversarial patch attacks solely based on the output of object detectors, without accessing the model or original images, by mapping normal attributes of bounding boxes and confidence vectors to calculate anomaly scores and mitigate attacks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing detection methods are used that require access to the model or image inputs, then detection capability is improved, but device complexity and real-time performance are worsened

Engineering Contradiction:
Improveattack detection capabilityVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the necessary detection functionality from complex model-access methods, creating a standalone detector that operates on output data alone. This eliminates the need for model integration while maintaining detection capability through a simplified architecture that processes only bounding box and confidence score data.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces an intermediary detection system that sits between the object detector and the application, analyzing output data without requiring access to the detector's internal model or input images. This intermediary layer enables attack detection while preserving the independence and simplicity of both the detector and application components.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If model-dependent detection methods are used, then detection accuracy is improved, but adaptability to different object detectors is worsened

Engineering Contradiction:
Improvedetection accuracyVSAvoidmodel-agnostic capability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal detection system that can identify adversarial attacks across multiple different object detector architectures (YOLO, SSD, Faster R-CNN) using a single model-agnostic approach. The detector analyzes common output structures (bounding boxes and confidence scores) rather than architecture-specific features, enabling broad applicability without sacrificing detection accuracy.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

Instead of adapting the detection method to each specific detector model, the patent inverts the approach by having the detector adapt to standard output formats from various models. This reversal enables a single detection system to serve multiple detector types without requiring custom integration for each model.

Inventive Principle:
Principle #13The other way round (Inversion)

3Reliability

If existing attack detection methods are deployed, then security is improved, but processing speed and real-time performance are worsened

Engineering Contradiction:
Improvesystem securityVSAvoidreal-time processing speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent employs a lightweight detection model that processes data quickly and discards results after each frame, enabling real-time operation. The simple architecture processes only essential output features without complex analysis, maintaining high processing speed while providing continuous security monitoring at video frame rates.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The patent performs partial analysis by focusing only on the most critical aspects of detector output (bounding box confidence scores and spatial relationships) rather than comprehensive model analysis. This selective approach provides sufficient security detection while maintaining real-time processing capability.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4462322A1A method and a system for real-time detection of attacks on ai-based object detectors
Publication Date: 2024.11.13 DEUTSCHE TELEKOM AG
  • EP4462322A1 patent drawingFigure 1~2B
  • EP4462322A1 patent drawingFigure 3~4
  • EP4462322A1 patent drawing

AI summary

An Al-based method for real-time detection and mitigation of attacks on object detectors being fed by input images acquired by one or more imagers, comprising the steps of mapping normal attributes of the outputs of an ML-model associated with the object detectors, using unsupervised learning; creating an anomaly detection model being capable of identifying adversarial attacks in the form of adversarial patchs, based solely on the outputs of the object detectors and without accessing the object detectors model or any original frames aquired by the one or more imagers; calculating the anomaly score for each object being detected by the ML-model object detectors; comparing the anomaly scores of the detected objects to a preset threshold; protecting the object detectors agaist the attacks by identifying and mitigating the effects of the adversarial patch attacks using the comparison results.