3 papers
cs.CV2025
Evading Data Provenance in Deep Neural Networks
Hongyu Zhu, Sichu Liang, Wenwen Wang +3
Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. Howeve…
cs.CV2025
Revisiting Data Auditing in Large Vision-Language Models
Hongyu Zhu, Sichu Liang, Wenwen Wang +5
With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great poten…
cs.CV2025
PromptLA: Towards Integrity Verification of Black-box Text-to-Image Diffusion Models
Zhuomeng Zhang, Fangqi Li, Chong Di +3
Despite the impressive synthesis quality of text-to-image (T2I) diffusion models, their black-box deployment poses significant regulatory challenges: Malicious actors can fine-tune…