Junqi Wu

Orcid: 0009-0005-9533-332X

Affiliations:
  • Shanghai Jiao Tong University, China
  • Chinese Academy of Military Science, Defense Innovation Institute, Beijing, China
  • Sun Yat-sen University, School of Data and Computer Science, Guangdong Key Laboratory of Information Security Technology, Guangzhou, China (former)


According to our database1, Junqi Wu authored at least 8 papers between 2020 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models.
CoRR, April, 2026

2025
Improving the Transferability of Adversarial Examples by Feature Augmentation.
IEEE Trans. Neural Networks Learn. Syst., September, 2025

Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations.
CoRR, September, 2025

Gradient-based sparse voxel attacks on point cloud object detection.
Pattern Recognit., 2025

CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

2024
Improving the Transferability of Adversarial Examples by Feature Augmentation.
CoRR, 2024

2023
Impact of Light and Shadow on Robustness of Deep Neural Networks.
CoRR, 2023

2020
Audio Steganography Based on Iterative Adversarial Attacks Against Convolutional Neural Networks.
IEEE Trans. Inf. Forensics Secur., 2020


  Loading...