Stealthy Targeted Poisoning Attacks in Vertical Split Learning via Embedding Model Manipulation

Vertical split learning (VSL, a privacy method that divides an AI model between multiple clients and a server) has been found vulnerable to a new stealthy attack called TPA-VSL, where attackers manipulate the embedding model (the part that converts data into numerical vectors) to misclassify targeted samples without leaving obvious signs of poisoning. The attack uses diffusion models (AI systems that generate data by reversing a noise process) and special encoders to trick the system into mapping target data to wrong classes, achieving a 30% higher success rate than existing attacks.