paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
FL

Fenghua Li

ACL 2026SIGIR 2026安全效率与系统可解释性检索与知识
新星分资深
25
一作贡献0
核心/参与9
方向广度11
合作网络9
0 一作 · 2 篇 · ACL 2026 / SIGIR 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

2
作者位次 #6/7ACL 2026Findings· Findings of ACL

Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference

Yang Lyu · Jin Cao · Yang Xiao · Zhe Sun · Ben Niu · Fenghua Li · Hui Li

摘要

Distributed LLM inference avoids sending raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy. We challenge this assumption and demonstrate that intermediate representations alone are sufficient to leak sensitive user attributes. This setting poses...

安全可解释性效率与系统OpenReview 项目页
作者位次 #6/6SIGIR 2026Oral· Information Retrieval (Full)

How Far Are We from Automatically Identifying Violations of the Data Minimization Principle in Privacy Policies?

Ziyan Zhou · Yanru He · Yunchuan Guo · Haoyang Yu · Liang Fang · Fenghua Li

摘要

Data protection laws and regulations require service providers to disclose data practices in privacy policies, specifying what personal information is processed and for what purposes. For compliance, these data practices must adhere to the data minimization principle, limiting the processing of p...

检索与知识安全效率与系统OpenReview

常见合作者