2 papers
cs.SE2026
What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays
Xiaodong Wu, Zhimin Zhao, Qi Li +3
Third-party application programming interface (API) relays offer access to large language models (LLMs), often at lower prices. Users depend on these services for model quality, in…
cs.CR2026
WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models
Jie Cao, Qi Li, Chaklam Cheong +4
Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of-the-art (SOTA) removal attacks can suppress embedded signal…