Publications by categories in reversed chronological order. * denotes equal contribution.


  1. preprint
    To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images... For Now
    Yimeng Zhang*, Jinghan Jia*, Xin Chen, and 5 more authors
    arXiv preprint arXiv:2310.11868 2023
  2. preprint
    DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
    Aochuan Chen, Yimeng Zhang, Jinghan Jia, and 7 more authors
    In arxiv 2310.02025 Oct 2023
  3. NeurIPS’23
    Model sparsification can simplify machine unlearning
    Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, and 5 more authors
    arXiv preprint arXiv:2304.04934 Oct 2023
  4. NeurIPS’23
    Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
    Yihua Zhang, Yimeng Zhang, Aochuan Chen, and 6 more authors
    In Thirty-seventh Conference on Neural Information Processing Systems Oct 2023
  5. SANER’23
    CLAWSAT: Towards Both Robust and Accurate Code Models
    Jinghan Jia*, Shashank Srikant*, Tamara Mitrovska, and 4 more authors
    Oct 2023


  1. ICLR’22
    How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
    Yimeng Zhang, Yuguang Yao, Jinghan Jia, and 4 more authors
    arXiv preprint arXiv:2203.14195 Oct 2022
  2. TSRML’22
    On the Robustness of deep learning-based MRI Reconstruction to image transformations
    Jinghan Jia, Mingyi Hong, Yimeng Zhang, and 2 more authors
    arXiv preprint arXiv:2211.04930 Oct 2022


  1. ISMRM
    Instabilities in Conventional Multi-Coil MRI Reconstruction with Small Adversarial Perturbations
    Chi Zhang*, Jinghan Jia*, Burhaneddin Yaman, and 4 more authors
    In 2021 55th Asilomar Conference on Signals, Systems, and Computers Oct 2021