8 papers
Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
Xiaoyu Luo, Wenrui Yu, Qiongxiu Li +1
Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusi…
When Is Distributed Nonlinear Aggregation Private? Optimality and Information-Theoretical Bounds
Wenrui Yu, Jaron Skovsted Gundersen, Richard Heusdens +1
Nonlinear aggregation is central to modern distributed systems, yet its privacy behavior is far less understood than that of linear aggregation. Unlike linear aggregation where mat…
LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization
Wenrui Yu, Yiyi Chen, Johannes Bjerva +2
We propose LAGO - Language Similarity-Aware Graph Optimization - a novel approach for few-shot cross-lingual embedding inversion attacks, addressing critical privacy vulnerabilitie…
Byzantine-Resilient Federated Learning via Distributed Optimization
Yufei Xia, Wenrui Yu, Qiongxiu Li
Byzantine attacks present a critical challenge to Federated Learning (FL), where malicious participants can disrupt the training process, degrade model accuracy, and compromise sys…
Optimal Privacy-Preserving Distributed Median Consensus
Wenrui Yu, Qiongxiu Li, Richard Heusdens +1
Distributed median consensus has emerged as a critical paradigm in multi-agent systems due to the inherent robustness of the median against outliers and anomalies in measurement. D…
From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges
Qiongxiu Li, Wenrui Yu, Yufei Xia +1
Federated Learning (FL) enables collaborative learning without directly sharing individual's raw data. FL can be implemented in either a centralized (server-based) or decentralized…