publications
Publications in reversed chronological order. (* indicates equal contribution).
2026
- preprintTherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy ChatbotsFangrui Huang, Souhad Chbeir, Arpandeep Khatua, Sheng Wang, Sijun Tan, Kenan Ye, Lily Bailey, Merryn Daniel, Ryan Louie, Sanmi Koyejo, and Ehsan Adeli2026
- ICMLV1: Unifying Generation and Self-Verification for Parallel ReasonersHarman Singh*, Xiuyu Li*, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki, Rishabh Tiwari, Long Lian, Yucheng Lu, Boyi Li, Alane Suhr, Ben Athiwaratkun, and Kurt KeutzerInternational Conference on Machine Learning (ICML), 2026
- ICLRAuditing Black-Box LLM APIs with a Rank-Based Uniformity TestXiaoyuan Zhu, Yaowen Ye, Tianyi Qiu, Hanlin Zhu, Sijun Tan, Ajraf Mannan, Jonathan Michala, Raluca Ada Popa, and Willie Neiswanger2026
2025
- WorkshopBudget-aware Test-time Scaling via Discriminative VerificationKyle Montgomery*, Sijun Tan*, Yuqi Chen, Siyuan Zhuang, Tianjun Zhang, Raluca Ada Popa, and Chenguang WangNeurIPS 2025 Workshop on Efficient Reasoning, 2025
- NotionDeepSWE: Training a State-of-the-Art Coding Agent from Scratch by Scaling RLMichael Luo^, Naman Jain^, Jaskirat Singh^, Sijun Tan^, Ameen Patel^, Qingyang Wu^, Alpay Ariyak^, Colin Cai^, Tarun Venkat, Shang Zhu, Ben Athiwaratkun, Manan Roongta, Ce Zhang, Li Erran Li, Raluca Ada Popa, Koushik Sen, and Ion Stoica2025
2024
- preprintProof of Sampling: A Nash Equilibrium-Secured Verification Protocol for Decentralized SystemsYue Zhang*, Shouqiao Wang*, Sijun Tan*, Xiaoyuan Liu, Raluca Ada Popa, and Ciamac C. Moallemi2024
2023
- IEEE S&PMPCAuth: Multi-factor Authentication for Distributed-trust SystemsSijun Tan, Weikeng Chen, Ryan Deng, and Raluca Ada PopaIEEE Symposium on Security and Privacy (Oakland), 2023
Systems with distributed trust have attracted growing research attention and seen increasing industry adoptions. In these systems, critical secrets are distributed across N servers, and computations are performed privately using secure multi-party computation (SMPC). Authentication for these distributed-trust systems faces two challenges. The first challenge is ease-of-use. Namely, how can an authentication protocol maintain its user experience without sacrificing security? To avoid a central point of attack, a client needs to authenticate to each server separately. However, this would require the client to authenticate N times for each authentication factor, which greatly hampers usability. The second challenge is privacy, as the client’s sensitive profiles are now exposed to all N servers under different trust domains, which creates N times the attack surface for the profile data. To address both challenges, we present MPCAuth, a multi-factor authentication system for distributed-trust applications. Our system enables a client to authenticate to N servers independently with the work of only one authentication. In addition, our system is profile hiding, meaning that the client’s authentication profiles such as her email username, phone number, passwords, and biometric features are not revealed unless all servers are compromised. We propose secure and practical protocols for an array of widely adopted authentication factors, including email passcodes, SMS messages, U2F, security questions/passwords, and biometrics. Our system finds practical applications in the space of cryptocurrency custody and collaborative machine learning, and benefits future adoptions of distributed-trust applications.
- ACSACSecure Softmax/Sigmoid for Machine-learning ComputationYu Zheng, Qizhi Zhang, Sherman S. M. Chow, Yuxiang Peng, Sijun Tan, Lichun Li, and Shan YinIn Proceedings of the 39th Annual Computer Security Applications Conference (ACSAC), 2023
2021
- IEEE S&PCryptGPU: Fast Privacy Preserving Machine Learning on the GPUSijun Tan, Brian Knott, Yuan Tian, and David J WuIEEE Symposium on Security and Privacy (Oakland), 2021
We introduce CryptGPU, a system for privacy-preserving machine learning that implements all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in the success of modern deep learning, they are also essential for realizing scalable privacy-preserving deep learning. In this work, we start by introducing a new interface to losslessly embed cryptographic operations over secret-shared values (in a discrete domain) into floating-point operations that can be processed by highly-optimized CUDA kernels for linear algebra. We then identify a sequence of "GPU-friendly" cryptographic protocols to enable privacy-preserving evaluation of both linear and non-linear operations on the GPU. Our microbenchmarks indicate that our private GPU-based convolution protocol is over 150× faster than the analogous CPU-based protocol; for non-linear operations like the ReLU activation function, our GPU-based protocol is around 10× faster than its CPU analog. With CryptGPU, we support private inference and training on convolutional neural networks with over 60 million parameters as well as handle large datasets like ImageNet. Compared to the previous state-of-the-art, our protocols achieve a 2× to 8× improvement in private inference for large networks and datasets. For private training, we achieve a 6× to 36× improvement over prior state-of-the-art. Our work not only showcases the viability of performing secure multiparty computation (MPC) entirely on the GPU to newly enable fast privacy-preserving machine learning, but also highlights the importance of designing new MPC primitives that can take full advantage of the GPU’s computing capabilities.
- NeurIPSLeast Square Calibration for Peer ReviewsSijun Tan*, Jibang Wu*, Xiaohui Bei, and Haifeng XuConference on Neural Information Processing Systems (NeurIPS) 2021