Zhen Li

This paper evaluates the vulnerability of Fully Homomorphic Encryption (FHE) computation to silent data corruption (SDC) using large-scale fault-injection experiments and theoretical analysis.

This paper develops improved Gaussian mechanisms for Rényi Pufferfish Privacy (RPP) by incorporating Gaussian and Gaussian-mixture priors, significantly reducing the required noise and improving the privacy-utility trade-off.

This paper introduces an active traffic analysis method (NATA) and a deep learning framework (BM-Net) to demonstrate that bandwidth perturbations can be used by an adversary to correlate and de-anonymize Tor traffic flows.

FT-Pilot is a novel GNN-guided LLM framework that automatically rewrites RTL code to harden digital circuits against soft errors, providing an efficient, automated path for reliability optimization.

CoMIC is a cloud-edge framework that enables resource-constrained LLM agents to successfully complete complex, long-horizon tasks by collaboratively sharing and refining memory and insights between local edge devices and a central cloud critic.

The paper introduces Drifting Preference Optimization (DrPO), an efficient online method for preference finetuning one-step text-to-image generators that avoids complex gradient calculations and model dependencies.