Zeyao Liu — accepted AI-conference papers

2026

Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures

Zeyao Liu, Zhendong Zhao, Xiaojun Chen, Xin Zhao, Yuexin Xuan, Xiaoshuang Ji

CVPR 2026

Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the Visual Parameter-Efficient Fine-Tuning (PEFT) paradigm, dominated by adapter-based (e.g., LoRA) and prompt-based (e.g., V

Cited by 0 Source ↗Scholar ↗

2026

Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image Generation

Xin Zhao, Xiaojun Chen, Bingshan Liu, Zeyao Liu, Zhendong Zhao, Xiaoyan Gu

AAAI 2026technical

Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose substantial risks of producing unsafe, offensive, or culturally inappropriate content when prompted adversarially. Current defenses struggle to align outputs wi

Cited by 0 Source ↗PDF ↗Scholar ↗