Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
Researchers are developing methods to create adversarial patches that can fool vision-language models (VLMs) used in autonomous driving. These patches, when physically applied, can cause systems to miss pedestrians or misinterpret road conditions. Studies show high transferability rates between different VLM architectures, meaning an attack optimized for one model can still be effective against others, posing a significant safety risk. AI
IMPACT New research highlights significant vulnerabilities in autonomous driving perception systems, potentially requiring new defense mechanisms against adversarial attacks.