3 papers
cs.CR2026
Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning
Wenhao Wang, Shujie Cui, Hui Cui +1
Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used to protect training data in machine learning. Its privacy guarantee is commonly analyzed through a securi…
cs.CL2026
Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
Chenchen Tan, Youyang Qu, Xinghao Li +4
The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential reten…
cs.CR2025
Guard-GBDT: Efficient Privacy-Preserving Approximated GBDT Training on Vertical Dataset
Anxiao Song, Shujie Cui, Jianli Bai +3
In light of increasing privacy concerns and stringent legal regulations, using secure multiparty computation (MPC) to enable collaborative GBDT model training among multiple data o…