AI Examples

Examples of AI applications

In order to categorize AI mobile and edge applications into several classes regarding their security goals, a functional evaluation was performed for numerous existing AI applications in this project. The evaluated applications originate from a wide scope (biometry, smart home, smart living, smart devices, etc.), to identify a general classification that suits a variety of applications. From this functional evaluation several classes were derived.

Below, four different applications will be evaluated along with its determined classes, showing how a classification can be achieved and to validate that the determined classes may be applied to numerous AI applications.




Gang-Authentifizierung (Seamless.me)
Category Partial aspect
Input Where does the data come from?
  • Sensors
Number of data classes?
  • One Class Classification / Novelty Detection
Type of data?
  • Sensor data
Training Where does training take place?
  • decentral, decoupled
When is new training data added?
  • continuous (online learning)
Modell Where is the model deployed?
  • on-device
What is known?
  • Supervised Learning
  • own histogramm-based novelty detector
  • Scikit-learn framework
Output What does the output look like?
  • Probability Scores
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Category Partial aspect
Input Where does the data come from?
  • Sensors
Number of data classes?
  • Multiclass
Type of data?
  • Image
Training Where does training take place?
  • decentral, decoupled
When is new training data added?
  • once when model is deployed
Modell Where is the model deployed?
  • on-device
What is known?
  • Supervised Learning
  • GAN
  • Tensorflow
Output What does the output look like?
  • Image, Generation Simularity Score
Realtime Object Recognition (YOLObile)
Category Partial aspect
Input Where does the data come from?
  • explicit user input
Number of data classes?
  • Multiclass
Type of data?
  • Image
Training Where does training take place?
  • zentral
When is new training data added?
  • once when model is deployed
Modell Where is the model deployed?
  • on-device
What is known?
  • Supervised Learning
  • DNN, group Lasso method
  • YOLOv4
Output What does the output look like?
  • Klassifizierung und Bounding Boxes
Object Detection (R-CNN)
Category Partial aspect
Input Where does the data come from?
  • explicit user input
Number of data classes?
  • Multiclass
Type of data?
  • Image
Training Where does training take place?
  • -
When is new training data added?
  • once when model is deployed
Modell Where is the model deployed?
  • on-device
What is known?
  • Supervised Learning
  • CNN
  • Tensorflow
Output What does the output look like?
  • classification

Last modified May 24, 2022: fix visual issues (e.g. dots) (36924f6)