Xiaomei Zhang

Xiaomei Zhang

Auto-generated profile, based on publicly available information

Xiaomei Zhang

School of Information and Communication Technology, Griffith University, Nathan, Australia

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2023
Verified
Conference Paper
Open access
XZXiaomei Zhang
Xiaomei Zhang
ZZZhaoxi Zhang
Zhaoxi Zhang
QZQi Zhong
Qi Zhong
XZXufei Zheng
Xufei Zheng
YZYanjun Zhang
Yanjun Zhang
LZLeo Yu Zhang
Leo Yu Zhang

21 November 2025 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
XZXiaomei Zhang
Xiaomei Zhang
ZZZhaoxi Zhang
Zhaoxi Zhang
YZYanjun Zhang
Yanjun Zhang
XZXufei Zheng
Xufei Zheng
LZLeo Yu Zhang
Leo Yu Zhang
SPShirui Pan
Shirui Pan
Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from the underlying manifold of normal texts, whereas pre-trained masked language models can approximate the manifold of normal data. These findings inspire the exploration of masked language models for detecting textual adversarial attacks. We first introduce Masked Language Model-based Detection (MLMD), leveraging the mask and unmask operations of the masked language modeling (MLM) objective to induce the difference in manifold changes between normal and adversarial texts. Although MLMD achieves competitive detection performance, its exhaustive one-by-one masking strategy introduces significant computational overhead. Our posterior analysis reveals that a significant number of non-keywords in the input are not important for detection but consume resources. Building on this, we introduce Gradient-guided MLMD (GradMLMD), which leverages gradient information to identify and skip non-keywords during detection, significantly reducing resource consumption without compromising detection performance. Extensive experiments show that GradMLMD maintains comparable or better performance than MLMD and outperforms existing detectors. Among defenses based on the off-manifold conjecture, GradMLMD presents a novel method for capturing manifold changes and provides a practical solution for real-world application challenges.