Juanjuan Weng

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 12

Top Topics

Countermeasures

Top Venues

IEEE Trans. Inf. Forensics Secur.

IEEE Trans. Pattern Anal. Mach. Intell.

Publications

Kejia Zhang, Juanjuan Weng, Yuanzheng Cai, Zhiming Luo, Shaozi Li
Mitigating Low-Frequency Bias: Feature Recalibration and Frequency Attention Regularization for Adversarial Robustness. CoRR (2024)
Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li
Comparative evaluation of recent universal adversarial perturbations in image classification. Comput. Secur. 136 (2024)
Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li
Learning transferable targeted universal adversarial perturbations by sequential meta-learning. Comput. Secur. 137 (2024)
Kejia Zhang, Juanjuan Weng, Junwei Wu, Guoqing Yang, Shaozi Li, Zhiming Luo
Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness. CoRR (2024)
Juanjuan Weng, Zhiming Luo, Shaozi Li
Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability. CoRR (2024)
Juanjuan Weng, Zhiming Luo, Shaozi Li
Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing. CoRR (2024)
Juanjuan Weng, Zhiming Luo, Shaozi Li, Nicu Sebe, Zhun Zhong
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration. IEEE Trans. Inf. Forensics Secur. 18 (2023)
Juanjuan Weng, Zhiming Luo, Zhun Zhong, Dazhen Lin, Shaozi Li
Exploring Non-target Knowledge for Improving Ensemble Universal Adversarial Attacks. AAAI (2023)
Juanjuan Weng, Zhiming Luo, Zhun Zhong, Shaozi Li, Nicu Sebe
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration. CoRR (2023)
Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li
Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification. CoRR (2023)
Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li, Zhun Zhong
Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature. CoRR (2023)
Fengxiang Yang, Juanjuan Weng, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Donglin Cao, Shaozi Li, Shin'ichi Satoh, Nicu Sebe
Towards Robust Person Re-Identification by Defending Against Universal Attackers. IEEE Trans. Pattern Anal. Mach. Intell. 45 (4) (2023)