Yunfei Li

Dr. Yunfei Li


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
4 May 2026 in Entropy
Verified
Journal Article
Open access
PDF file
JWJin Wei
Jin Wei
XWXinyuan Wang
Xinyuan Wang
LXLiam Xu
Liam Xu
YLYunfei Li
Yunfei Li
Multimodal models such as CLIP and ALBEF essentially maximize cross-modal mutual information to align heterogeneous modalities, utilizing semantic consistency as an implicit prior. However, this alignment mechanism creates a structural vulnerability: the models rely heavily on invariant information coupling. In this work, we investigate this vulnerability and propose a symmetry-driven adversarial attack framework. Unlike standard methods that inject high-entropy unstructured noise, our approach designs collaborative perturbations by modeling semantic-consistent mappings between geometric image transformations and syntactic text variations. By explicitly exploiting the information redundancy inherent in cross-modal symmetries, our method effectively reduces the entropy of the adversarial search space. This reveals a fundamental trade-off between information invariance and robustness, achieving state-of-the-art attack success rates with imperceptible perturbations.