publications

2025

  1. NeurIPS
    Pin the Tail on the Model: Blindfolded Repair of User-Flagged Failures in Text-to-Image Services
    Gefei Tan, Ali Shahin Shamsabadi, Ellen Kolesnikova, Hamed Haddadi, and Xiao Wang
    In Advances in Neural Information Processing Systems, 2025
    The first two authors contributed equally to this work.
  2. CCS
    Founding Zero-Knowledge Proofs of Training on Optimum Vicinity
    Gefei Tan, Adrià Gascón, Sarah Meiklejohn, Mariana Raykova, Xiao Wang, and Ning Luo
    In CCS 2025: ACM Conference on Computer and Communications Security, 2025

2024

  1. ESORICS
    Privacy-Preserving Regular Expression Matching using TNFA
    Ning Luo, Chenkai Weng, Jaspal Singh, Gefei Tan, Ruzica Piskac, and Mariana Raykova
    In ESORICS 2024: 29th European Symposium on Research in Computer Security, 2024
  2. ICLR
    Confidential-DPproof: Confidential Proof of Differentially Private Training
    Ali Shahin Shamsabadi, Gefei Tan, Tudor Ioan Cebere, Aurélien Bellet, Hamed Haddadi, Nicolas Papernot, Xiao Wang, and Adrian Weller
    In ICLR 2024: The Twelfth International Conference on Learning Representations, 2024
    Spotlight Paper (top 5%)

2023

  1. VLDB
    RESCU-SQL: Oblivious Querying for the Zero Trust Cloud
    Xiling Li, Gefei Tan, Xiao Wang, Jennie Rogers, and Soamar Homsi
    Proceedings of the VLDB Endowment, 2023
    The first two authors contributed equally to this work.

2022

  1. ICLR
    Reproducible Subjective Evaluation
    Max Morrison, Brian Tang, Gefei Tan, and Bryan Pardo
    In ICLR Workshop on Machine Learning Evaluation Standards, 2022