Jiawen Zhang (Zhejiang University), Xinpeng Yang (Zhejiang University), Lipeng He (University of Waterloo), Kejia Chen (Zhejiang University), Wen-jie Lu (Zhejiang University), Yinghao Wang (Zhejiang University), Xiaoyang Hou (Zhejiang University), Jian Liu (Zhejiang University), Kui Ren (Zhejiang University), Xiaohu Yang (Zhejiang University)

Secure transformer inference has emerged as a prominent research topic following the proliferation of ChatGPT. Existing solutions are typically interactive, involving substantial communication load and numerous interaction rounds between the client and the server.

In this paper, we propose NEXUS, the first non-interactive protocol for secure transformer inference. The protocol requires the client to engage in just one round of communication with the server during the whole inference process: submitting an encrypted input and receiving an encrypted result.
NEXUS introduces several novel primitives, including SIMD ciphertext compression/decompression, SIMD slot folding, and secure Argmax, which enable it to significantly surpass the state-of-the-art in communication while maintaining comparable runtime. Specifically, it reduces bandwidth consumption by 372.5$times$ compared to BOLT (Oakland~'24) and 53.6$times$ compared to Bumblebee (NDSS~'25). Furthermore, its non-interactive property allows for optimal hardware acceleration, with the GPU version achieving a 42.3$times$ speedup in runtime. This enables NEXUS to run inference on a BERT-based model in just 37.3 seconds, consuming only 164~MB of bandwidth.

View More Papers

Welcome to Jurassic Park: A Comprehensive Study of Security...

Abdullah AlHamdan (CISPA Helmholtz Center for Information Security), Cristian-Alexandru Staicu (CISPA Helmholtz Center for Information Security)

Read More

The Forking Way: When TEEs Meet Consensus

Annika Wilde (Ruhr University Bochum), Tim Niklas Gruel (Ruhr University Bochum), Claudio Soriente (NEC Laboratories Europe), Ghassan Karame (Ruhr University Bochum)

Read More

TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents

Chen Gong (University of Vriginia), Kecen Li (Chinese Academy of Sciences), Jin Yao (University of Virginia), Tianhao Wang (University of Virginia)

Read More