Wangli Yang
Biographic Data
| ID | 6536664 |
|---|---|
| NAME | Wangli Yang |
| GIVEN NAMES | Wangli |
| FAMILY NAME | Yang |
| SIGNATURE | YANG W |
| AFFILIATIONS | School of Computing and Information Technology, University of Wollongong. [email protected] |
| VERIFIED | No |
| TOTAL WORKS | 1 |
| TOTAL CITATIONS | 0 |
| WORKS AS AUTHOR | 1 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2025 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 0 |
Defensive Dual Masking for Robust Adversarial Defense
Adversarial defenses for textual data have gained considerable attention in recent years due to the increasing vulnerability of Natural Language Processing (NLP) models to adversarial attacks. These attacks exploit subtle perturbations in input text to deceive models, posing significant challenges to model robustness and reliability. This article introduces Defensive Dual Masking (DDM), a simple yet effective algorithm that uses two unique maskin…
No prominent works on this page.
Defensive Dual Masking for Robust Adversarial Defense
Adversarial defenses for textual data have gained considerable attention in recent years due to the increasing vulnerability of Natural Language Processing (NLP) models to adversarial attacks. These attacks exploit subtle perturbations in input text to deceive models, posing significant challenges to model robustness and reliability. This article introduces Defensive Dual Masking (DDM), a simple yet effective algorithm that uses two unique maskin…
Adversarial Robustness in Machine Learning (1 work) · Adversarial system (1 work) · Exploit (1 work) · Inference (1 work) · Masking (illustration (1 work) · Physical Unclonable Functions (PUFs) and Hardware Security (1 work) · Robustness (evolution (1 work) · Scalability (1 work) · Subspace topology (1 work)