[1] Weng J, Luo Z, Li S, et al. Logit margin matters: Improving transferable targeted adversarial attack by logit calibration[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 3561-3574. (CCF-A 期刊 )
[2] Weng J, Luo Z, Zhong Z, et al. Exploring non-target knowledge for improving ensemble universal adversarial attacks[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37(3): 2768-2775. (CCF-A 会议, Oral)
[3] Weng, J, Luo Z, et al. Boosting Adversarial Transferability via Logits Mixup with Dominant Decomposed Feature. IEEE Transactions on Information Forensics and Security (2024). (CCF-A 期刊)
[4] Weng, J, Luo Z, et al. Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing”. IEEE Transactions on Information Forensics and Security (2025). (CCF-A 期刊)
[5] Yang F*, Weng J*, Zhong Z, et al. Towards robust person re-identification by defending against universal attackers[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(4): 5218-5235. (CCF-A 期刊, *Equal Contribution)
[6] He, Y., Peng, L., Zhang, Y., Weng, J.†, Li, S., & Luo, Z.†. Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail
AAAI Conference on Artificial Intelligence (2025). (CCF-A 会议, †通讯作者)
[7] Weng J, Luo Z, Lin D, et al. Comparative evaluation of recent universal adversarial perturbations in image classification[J]. Computers & Security, 2023: 103576. (CCF-B 期刊)
[8] Weng J, Luo Z, Lin D, et al. Learning transferable targeted universal adversarial perturbations by sequential meta-learning[J]. Computers & Security, 2024, 137: 103584. (CCF-B 期刊)