Howe Wang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1
Frequent co-authors
Research Timeline
2026
Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing
This paper investigates a novel security vulnerability where imperceptible branding hints can be injected into images and subsequently re-rendered onto new objects by generative AI models, proposing both attack scenarios and a robust mitigation solution.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 11, 2026
Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing
Desen Sun, Jason Hon, Howe Wang, Saarth Rajan +2 more
This paper investigates a novel security vulnerability where imperceptible branding hints can be injected into images and subsequently re-rendered onto new objects by generative AI models, proposing b…
View →