Xiaodong Wu (吴晓东)
≡
profile photo

Xiaodong Wu

Xiaodong Wu (吴晓东) is currently a PhD. student in Electronic and Computer Engineering Apartment at Queen's Univercity at Kingston, supervised by Professor Jianbing Ni. I work on the AI security including adversarial attacks, malware detection, trustworthy AI, etc. Before that, I did my masters at KAUST and bachelors at UESTC.

Email  /  Google Scholar  /  Github  / 

Publications

Conference (* equal contribution)

  1. SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
    Xiaodong Wu, Xiangman Li, Qi Li, Jianbing Ni, Rongxing Lu
    Accepted at Esorics 2025 | paper

  2. When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
    Xiaodong Wu, Tianyi Tang, Xiangman Li, Jianbing Ni, Yong Yu
    Accepted at ICICS 2025 | paper

  3. Accelerating secure and verifiable data deletion in cloud storage via SGX and blockchain
    Xiangman Li, Xiaodong Wu, Jianbing Ni
    GLOBECOM 2024-2024 IEEE Global Communications Conference | paper

  4. Think as People: Context-Driven Multi-Image News Captioning with Adaptive Dual Attention
    Qiang Yang, Xiaodong Wu, Xiuying Chen, Xin Gao, Xiangliang Zhang
    ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | paper

  5. Compositional Mathematical Encoding for Math Word Problems
    Zhenwen Liang, Jipeng Zhang, Kehan Guo, Xiaodong Wu, Jie Shao, Xiangliang Zhang
    Findings of the Association for Computational Linguistics: ACL 2023 | paper

  6. HG-Meta: Graph Meta-learning over Heterogeneous Graphs
    Qiannan Zhang, Xiaodong Wu, Qiang yang, Chuxu Zhang, Xiangliang Zhang
    Proceedings of the 2022 SIAM International Conference on Data Mining (SDM) | paper

  7. Few-shot Heterogeneous Graph Learning via Cross-domain Knowledge Transfer
    Qiannan Zhang, Xiaodong Wu, Qiang yang, Chuxu Zhang, Xiangliang Zhang
    Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2022 | paper

Journal (* equal contribution)

  1. Evaluating Security and Robustness for Split Federated Learning against Poisoning Attacks
    Xiaodong Wu, Henry Yuan, Xiangman Li, Jianbing Ni, Rongxing Lu
    IEEE Transactions on Information Forensics and Security 2024 | paper

  2. Unveiling security, privacy, and ethical concerns of ChatGPT
    Xiaodong Wu, Ran Duan, Jianbing Ni
    Journal of Information and Intelligence 2024 | paper

Preprint or under review (* equal contribution)

  1. SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
    Xiangman Li, Xiaodong Wu, Qi Li, Jianbing Ni, Rongxing Lu
    arXiv preprint arXiv:2508.15182 2025 | paper

  2. Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks
    Xiaodong Wu*, Xiangman Li*, Jianbing Ni
    arXiv preprint arXiv:2506.18543 2025 | paper

  3. PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
    Xiangman Li, Xiaodong Wu, Jianbing Ni, Mohamed Mahmoud, Maazen Alsabaan
    arXiv preprint arXiv:2506.15112 2025 | paper

  4. Manipulating Predictions over Discrete Inputs in Machine Teaching
    Xiaodong Wu, Yufei Han, Hayssam Dahrouj, Jianbing Ni, Zhenwen Liang, Xiangliang Zhang
    arXiv preprint arXiv:2401.17865 2024 | paper

Education

  1. Jan 2023 - Present,   Ph.D. candidate in Electronic and Computer Engineering,   Queen's University at Kingston, Canada

  2. Aug 2020 - Dec 2021,   M.S. in Computer Science,   King Abdullah University of Science and Technology, Saudi Arabia

  3. Sept 2016 - Jun 2020,   B.E. in Engineering,   University of Electronic Science and Technology of China, China

© Xiaodong Wu 吴晓东 | Last updated: May 2023
Template from Link .