Is this you? Claim this profile to correct it, add a bio and choose the work people see first.

Claim this profile

Works8 from public data

TitleCited by
  • Range Membership Inference Attacks

    Jiashu Tao, Reza Shokri

    IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · 2025

    It is shown that RaMIAs can capture privacy loss more accurately and comprehensively than MIAs on various types of data, such as tabular, image, and language, which paves the way for more comprehensive and meaningful privacy auditing of machine learning algorithms.

    15
  • Towards Overcoming False Positives in Visual Relationship Detection

    Daisheng Jin, Xiao Ma, Chongzhi Zhang, Yizhuo Zhou, Jiashu Tao, Mingyuan Zhang, Zhoujun Li

    British Machine Vision Conference (BMVC) · 2021

    Spatially-Aware Balanced negative pRoposal sAmpling (SABRA), a robust VRD framework that alleviates the influence of false positives and improves the spatial modeling ability of SABRA on two aspects: a simple and efficient multi-head heterogeneous graph attention network (MH-GAT) that models the global spatial interactions of objects, and a spatial mask decoder that learns the local spatial configuration.

    6
  • Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities

    Xudong Shen, Brown, Hannah, Jiashu Tao, Strobel, Martin, Yao Tong, Akshay Narayan, Harold Soh, Finale Doshi‐Velez

    arXiv · 2023

    This work investigates to what extent can AI experts vet an AI system for adherence to regulatory requirements through the lens of two public sector procurement checklists, identifying what can be done now, what should be possible with technical innovation, and what requirements need a more interdisciplinary approach.

    4
  • 4
  • Directions of Technical Innovation for Regulatable AI Systems

    Xudong Shen, Hannah Brown, Jiashu Tao, Martin Strobel, Yao Tong, Akshay Narayan, Harold Soh, Finale Doshi‐Velez

    Communications of the ACM · 2024

    3
  • (Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs

    Jiashu Tao, Reza Shokri

    arXiv · 2025

    It is shown that a simple token-based InfoRMIA can pinpoint which tokens are memorized within generated outputs, thereby localizing leakage from the sequence level down to individual tokens, while achieving stronger sequence-level inference power on LLMs.

    2
  • Machine Learning from Explanations

    Jiashu Tao, Reza Shokri

    arXiv · 2025

    –
  • Fleets of commercial vehicles

    Fanshu Geng, Yifan Li, Zhanpeng Sun, Jiashu Tao

    E3S Web of Conferences · 2021

    –

Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.

Report an error

Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.