collaborators

6 papers

cs.CR2025

The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

Rongzhe Wei, Peizhi Niu, Xinjie Shen +7

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the p…

cs.LG2025

Towards Universal Debiasing for Language Models-based Tabular Data Generation

Tianchun Li, Tianci Liu, Xingchen Wang +4

Large language models (LLMs) have achieved promising results in tabular data generation. However, inherent historical biases in tabular datasets often cause LLMs to exacerbate fair…

cs.LG2025

Differentially Private Relational Learning with Entity-level Privacy Guarantees

Yinan Huang, Haoteng Yin, Eli Chien +2

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Priva…

cs.CL2025

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Rongzhe Wei, Peizhi Niu, Hans Hao-Hsun Hsu +9

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of i…

cs.LG2025

Model Generalization on Text Attribute Graphs: Principles with Large Language Models

Haoyu Wang, Shikun Liu, Rongzhe Wei +1

Large language models (LLMs) have recently been introduced to graph learning, aiming to extend their zero-shot generalization success to tasks where labeled graph data is scarce. A…

cs.LG2024

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Rongzhe Wei, Mufei Li, Mohsen Ghassemi +7

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its r…