Zhong Wang
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×1AI×1
Frequent co-authors
Research Timeline
2026
Asking Back: Interaction-Layer Antidistillation Watermarks
The paper proposes interaction-layer antidistillation watermarks by embedding behavioral markers into the system prompt, which successfully track knowledge distillation even when paraphrasing attackers strip traditional token-level signals.
Backdooring Masked Diffusion Language Models
The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CRRecentMay 19, 2026
Backdooring Masked Diffusion Language Models
The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.
View →
cs.CRcs.AIRecentMay 15, 2026