Showing cs.CRShow all
3 papers · 1 filter
cs.CR2025
Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
Jinhua Yin, Peiru Yang, Chen Yang +5
Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models…
cs.CR2025
Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness
Peiru Yang, Xintian Li, Wanchun Ni +6
Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text (AIGT), serving as an important mechanism for AIGT detection. Ex…
cs.CR2025
Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes
Qi Tao, Yin Jinhua, Cai Dongqi +10
In light of scaling laws, many AI institutions are intensifying efforts to construct advanced AIs on extensive collections of high-quality human data. However, in a rush to stay co…