Get started
Author

Qiongxiu Li

Observed name: Li, Qiongxiu
Institution: Aalborg University
Observed institution: Aalborg University
OpenAlex ID: A5114534364
Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
2024 · Li, Xiao, Zhang, Wei, et al. · arXiv (Cornell University) · 1
PDF
When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning
2026 · Yu, Wenrui, Ji, Changlong, et al. · arXiv (Cornell University)
PDF
Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
2026 · Association for Computational Linguistics 2026, Bjerva, Johannes, et al. · Underline Science Inc.
SOMP: Scalable Gradient Inversion for Large Language Models via Subspace-Guided Orthogonal Matching Pursuit
2026 · Li, Yibo, Li, Qiongxiu · arXiv (Cornell University)
PDF
Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
2026 · Luo, Xiaoyu, Yu, Wenrui, et al. · arXiv (Cornell University)
PDF
Semantic Leakage from Image Embeddings
2026 · Chen, Yiyi, Xu, Qiongkai, et al. · arXiv (Cornell University)
PDF
Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
2026 · Luo, Xiaoyu, Chen, Yiyi, et al. · arXiv (Cornell University)
PDF
A Wolf in Sheep’s Clothing: Targeted Routing Hijacking in Federated RAG
2026 · Junjie Mu, Qiongxiu Li · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 9
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type