15 citations · 22 across the 4 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023★ 2 cited
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks
Zihan Guan, Mengxuan Hu, Zhongliang Zhou +3
Recently, the Segment Anything Model (SAM) has gained significant attention as an image segmentation foundation model due to its strong performance on various downstream tasks. How…
cs.CV2023★ 5 cited
Black-box Backdoor Defense via Zero-shot Image Purification
Yucheng Shi, Mengnan Du, Xuansheng Wu +3
Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attack…