| Attacks which do not kill training make adversarial learning stronger J Zhang, X Xu, B Han, G Niu, L Cui, M Sugiyama, M Kankanhalli ICML 2020, 2020 | 561 | 2020 |
| An LLM can Fool Itself: A Prompt-Based Adversarial Attack X Xu, K Kong, N Liu, L Cui, D Wang, J Zhang, M Kankanhalli ICLR 2024, 2024 | 169* | 2024 |
| Decision Boundary-aware Data Augmentation for Adversarial Training C Chen, J Zhang, X Xu, L Lyu, C Chen, T Hu, G Chen IEEE Transactions on Dependable and Secure Computing, 2022 | 32* | 2022 |
| Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization X Xu, J Zhang, F Liu, M Sugiyama, M Kankanhalli NeurIPS 2023, 2023 | 30 | 2023 |
| AutoLoRa: An Automated Robust Fine-Tuning Framework X Xu, J Zhang, M Kankanhalli ICLR 2024, 2024 | 24* | 2024 |
| Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection X Xu, J Zhang, F Liu, M Sugiyama, M Kankanhalli NeurIPS 2023 (spotlight), 2023 | 22 | 2023 |
| Privacy-Preserving Low-Rank Adaptation for Latent Diffusion Models Z Luo, X Xu, F Liu, YS Koh, D Wang, J Zhang AAAI 2025 (best paper award at CoLoRAI), 2024 | 18* | 2024 |
| Perplexity-aware Correction for Robust Alignment with Noisy Preferences K Kong, X Xu, D Wang, J Zhang, M Kankanhalli NeurIPS 2024, 2024 | 18 | 2024 |
| NoiLin: Improving adversarial training and correcting stereotype of noisy labels J Zhang, X Xu, B Han, T Liu, L Cui, G Niu, M Sugiyama Transactions on Machine Learning Research, 2022 | 13* | 2022 |
| Adversarial Attack and Defense for Non-Parametric Two-Sample Tests X Xu, J Zhang, F Liu, M Sugiyama, M Kankanhalli ICML 2022, 2022 | 2 | 2022 |
| Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM Y Guo, Z Xu, X Xu, YK Wong, L Nie, M Kankanhalli arXiv preprint arXiv:2412.15614, 2024 | | 2024 |
| Towards Robust Foundation Models: Adversarial Contrastive Learning J Zhang, X Xu The Third Blogpost Track at ICLR 2024, 2024 | | 2024 |
Jingfeng ZhangLecturer@University of Auckland & Scientist@RIKEN AIPVerified email at riken.jp
