3 papers
cs.CL2025
The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations
Yubo Zhu, Dongrui Liu, Zecheng Lin +3
Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods…
cs.CR2025
On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
Zijian Wang, Wei Tong, Tingxuan Han +4
Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-…
cs.CV2024
Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis
Songrui Wang, Yubo Zhu, Wei Tong +1
Text-to-image synthesis has become highly popular for generating realistic and stylized images, often requiring fine-tuning generative models with domain-specific datasets for spec…