Zihao Zhu

@inproceedings{zhu2026advchain,
  title = {AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models},
  author = {Zhu, Zihao and Wu, Xinyu and Hu, Gehan and Lyu, Siwei and Xu, Ke and Wu, Baoyuan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{zhang2024reliable,
  title = {Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization},
  author = {Zhang, Mingda and Zhu, Mingli and Zhu, Zihao and Wu, Baoyuan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@inproceedings{zhu2025unthinking,
  title = {To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models},
  author = {Zhu, Zihao and Zhang, Hongbao and Wang, Ruotong and Ke, Xu and Siwei, Lyu and Wu, Baoyuan},
  booktitle = {NeurIPS 2025 Workshop on Foundations of Reasoning in Language Models},
  year = {2025},
}

@article{wu2025defenses,
  title = {Defenses in adversarial machine learning: A survey},
  author = {Wu, Baoyuan and Zhu, Mingli and Zheng, Meixi and Zhu, Zihao and Wei, Shaokui and Zhang, Mingda and Chen, Hongrui and Yuan, Danni and Liu, Li and Liu, Qingshan},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2025},
}

@article{zheng2025blackboxbench,
  title = {BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks},
  author = {Zheng, Meixi and Yan, Xuanchen and Zhu, Zihao and Chen, Hongrui and Wu, Baoyuan},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2025},
}

@article{wu2025backdoorbench,
  title = {BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning},
  author = {Wu, Baoyuan and Chen, Hongrui and Zhang, Mingda and Zhu, Zihao and Wei, Shaokui and Yuan, Danni and Zhu, Mingli and Wang, Ruotong and Liu, Li and Shen, Chao},
  journal = {International Journal of Computer Vision (IJCV)},
  year = {2025},
}

@inproceedings{zhu2024vdc,
  title = {VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models},
  author = {Zhu, Zihao and Zhang, Mingda and Wei, Shaokui and Wu, Bingzhe and Wu, Baoyuan},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
}

@article{wang2024versatile,
  title = {Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers},
  author = {Wang, Ruotong and Chen, Hongrui and Zhu, Zihao and Liu, Li and Wu, Baoyuan},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2024},
}

@inproceedings{wu2022backdoorbench,
  title = {BackdoorBench: A Comprehensive Benchmark of Backdoor Learning},
  author = {Wu, Baoyuan and Chen, Hongrui and Zhang, Mingda and Zhu, Zihao and Wei, Shaokui and Yuan, Danni and Zha, Hongyuan},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
}

@inproceedings{zhu2022shallow,
  title = {From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering},
  author = {Zhu, Zihao},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year = {2022},
}

@article{yu2020cross,
  title = {Cross-Modal Knowledge Reasoning for Knowledge-based Visual Question Answering},
  author = {Yu, Jing and Zhu, Zihao and Wang, Yujing and Zhang, Weifeng and Hu, Yue and Tan, Jianlong},
  journal = {Pattern Recognition (PR)},
  year = {2020},
}

@inproceedings{zhu2020mucko,
  title = {Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering},
  author = {Zhu, Zihao and Yu, Jing and Wang, Yujing and Sun, Yajing and Hu, Yue and Wu, Qi},
  booktitle = {Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)},
  year = {2020},
}