AAAI 2024technical3 citations
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)
Zihan Guan, Mengxuan Hu, Zhongliang Zhou, Jielu Zhang, Sheng Li, Ninghao Liu
Abstract
Image segmentation is foundational to computer vision applications, and the Segment Anything Model (SAM) has become a leading base model for these tasks. However, SAM falters in specialized downstream challenges, leading to various customized SAM models. We introduce BadSAM, a backdoor attack tailored for SAM, revealing that customized models can harbor malicious behaviors. Using the CAMO dataset, we confirm BadSAM's efficacy and identify SAM vulnerabilities. This study paves the way for the development of more secure and customizable vision foundation models.
BibTeX
@article{Guan_Hu_Zhou_Zhang_Li_Liu_2024, title={BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30448}, DOI={10.1609/aaai.v38i21.30448}, abstractNote={Image segmentation is foundational to computer vision applications, and the Segment Anything Model (SAM) has become a leading base model for these tasks. However, SAM falters in specialized downstream challenges, leading to various customized SAM models. We introduce BadSAM, a backdoor attack tailored for SAM, revealing that customized models can harbor malicious behaviors. Using the CAMO dataset, we confirm BadSAM’s efficacy and identify SAM vulnerabilities. This study paves the way for the development of more secure and customizable vision foundation models.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Guan, Zihan and Hu, Mengxuan and Zhou, Zhongliang and Zhang, Jielu and Li, Sheng and Liu, Ninghao}, year={2024}, month={Mar.}, pages={23506-23507} }