Juanjuan Weng

According to our database, Juanjuan Weng authored at least 8 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Learning transferable targeted universal adversarial perturbations by sequential meta-learning.

Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li

Comput. Secur., February, 2024

Comparative evaluation of recent universal adversarial perturbations in image classification.

Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li

Comput. Secur., January, 2024

Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing.

Juanjuan Weng, Zhiming Luo, Shaozi Li

CoRR, 2024

Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability.

Juanjuan Weng, Zhiming Luo, Shaozi Li

CoRR, 2024

2023

Towards Robust Person Re-Identification by Defending Against Universal Attackers.

Fengxiang Yang, Juanjuan Weng, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Donglin Cao, Shaozi Li, Shin'ichi Satoh, Nicu Sebe

IEEE Trans. Pattern Anal. Mach. Intell., April, 2023

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration.

Juanjuan Weng, Zhiming Luo, Shaozi Li, Nicu Sebe, Zhun Zhong

IEEE Trans. Inf. Forensics Secur., 2023

Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature.

Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li, Zhun Zhong

CoRR, 2023

Exploring Non-target Knowledge for Improving Ensemble Universal Adversarial Attacks.

Juanjuan Weng, Zhiming Luo, Zhun Zhong, Dazhen Lin, Shaozi Li

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023