A comprehensive privacy assessment of LLMs.
The first automated guardrail for agents.
A comprehensive trustworthiness assessment of compressed LLMs.
We develop a chatbot for early dementia prevention and leverage LLMs to build digital twins to evaluate chatbots.
A new method for safely and robustly injecting watermark after training without training data.
We propose a new risk to published generative models that finetuning on generated samples can exacerbate the privacy leakage.
We make local LLMs to engineer privacy-preserving prompts that are transferrable for cloud models.
We propose a new metric to efficiently evaluate the privacy risks from gradient inversion and provides new insights.
We develop a hybrid federated learning for learning financial-crime predictive models from horizontal and vertical federated data structures.
We uncover the security risk of data-free distillation from a poisoned teacher and propose the first countermeasure.