SeoulTech Develops AI Framework to Assess Vision-System Robustness
2 Articles
2 Articles
SeoulTech develops AI framework to assess vision-system robustness
A new AI-based framework called AdvWT, developed by Seoul National University of Science and Technology (SeoulTech), has been used to demonstrate how naturally occurring damage to traffic signs can cause DNN-based vision systems to misclassify them. Testing the model across multiple AI architectures showed attack transferability and physical-world robustness, with researchers stating that training models with AdvWT-generated damaged signs could …
SeoulTech develops AI framework to assess vision-system robustness | ADAS & Autonomous Vehicle International
A new AI-based framework called AdvWT, developed by Seoul National University of Science and Technology (SeoulTech), has been used to demonstrate how naturally occurring damage to traffic signs can cause DNN-based vision systems to misclassify them. Testing across multiple AI architectures showed attack transferability and physical-world robustness, with researchers stating that training models with AdvWT-generated damaged signs could help ident…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium




