Ziqing Yang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1Vision×1
Frequent co-authors
Research Timeline
2026
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
The paper introduces BadBone, a stealthy and adaptive backdoor attack that compromises a backbone model specifically to target downstream tasks utilizing prompt learning, demonstrating high attack success rates against state-of-the-art defenses.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.CVRecentMay 29, 2026
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
Ziqing Yang, Rui Wen, Xinlei He, Yun Shen +2 more
The paper introduces BadBone, a stealthy and adaptive backdoor attack that compromises a backbone model specifically to target downstream tasks utilizing prompt learning, demonstrating high attack suc…
View →