AINeutralarXiv – CS AI · 6h ago6/10
🧠
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
Researchers have developed a new technique called Shallow Semantic Camouflage (SSC) to protect personal data from unauthorized use in AI model training. The work addresses a critical gap where existing data protection methods fail under modern pretraining-finetuning paradigms, demonstrating that frozen pretrained weights significantly weaken previous unlearnable example approaches.