Black-box Targeted Adversarial Attack on Segment Anything (SAM)

arXiv:2310.10010v2 Announce Type: replace
Abstract: Deep recognition models are widely vulnerable to adversarial examples, which change the model output by adding quasi-imperceptible perturbation to the image input. Recently, Segment Anything Model (SAM) has emerged to become a popular foundation model in computer vision due to its impressive generalization to unseen data and tasks. Realizing flexible attacks on SAM is beneficial for understanding the robustness of SAM in the adversarial context. To this end, this work aims to achieve a targeted …

abstract adversarial adversarial examples arxiv become box change computer computer vision cs.cv data examples foundation foundation model image popular recognition sam segment segment anything segment anything model type vision vulnerable