Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/4NeurIPS 2026Poster

Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects

Xiaoyu Luo · Wenrui Yu · Qiongxiu Li · Johannes Bjerva

理论与学习动力学长上下文与架构OpenReview

作者位次 #3/4ACL 2026Poster· Natural Language Processing

Do LLM s Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework

Xiaoyu Luo · Yiyi Chen · Qiongxiu Li · Johannes Bjerva

摘要

Large Language Models (LLMs) have been reported to “leak” Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorization. We propose a principled revision of memorization evaluation for LLMs, arguing that PII leakage should be evaluated...

安全可解释性多模态OpenReview 项目页

作者位次 #4/4CCS 2026Oral· Computer & Communications Security

When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning

Wenrui Yu · Changlong Ji · Johannes Bjerva · Qiongxiu Li

安全OpenReview

Qiongxiu Li

获取完整研究档案

联系方式

2026 顶会论文

Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects

Do LLM s Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework

When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning

常见合作者