5 papers
APEX: Probing Neural Networks via Activation Perturbation
Tao Ren, Xiaoyu Luo, Qiongxiu Li
Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural informa…
Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
Xiaoyu Luo, Yiyi Chen, Qiongxiu Li +1
Large Language Models (LLMs) have been reported to "leak" Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorizatio…
Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
Xiaoyu Luo, Yiyi Chen, Johannes Bjerva +1
We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectur…
Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond
Qiongxiu Li, Xiaoyu Luo, Yiyi Chen +1
The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data.…
DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization
Xiaoyu Luo, Qiongxiu Li
Adversarial robustness, the ability of a model to withstand manipulated inputs that cause errors, is essential for ensuring the trustworthiness of machine learning models in real-w…