Backdoor Attacks on Video Segmentation Models

This paper addresses a critical security vulnerability in prompt-driven Video Segmentation Foundation Models (VSFMs), which are increasingly used in safety-critical applications. It highlights the ineffectiveness of existing backdoor attack methods and proposes a novel, two-stage framework (BadVSFM) specifically designed to inject backdoors into these models. The research is significant because it reveals a previously unexplored vulnerability and demonstrates the potential for malicious actors to compromise VSFMs, potentially leading to serious consequences in applications like autonomous driving.