Transferable Adversarial Attacks on SAM and Its Downstream Models
Transferable Adversarial Attacks on SAM and Its Downstream Models
The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats of adverse usage. This paper, for the first time, explores the feasibility of adversarial attacking various downstream …