Shangyi Shi

Shangyi Shi

Auto-generated profile, based on publicly available information

Shangyi Shi

Chinese Academy of Sciences

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 February 2023 in Analytica Chimica Acta
Verified
Journal Article
Closed access
HCHaoxiang Chen
Haoxiang Chen
BLBangying Li
Bangying Li
SSShangyi Shi
Shangyi Shi
TZTao Zhou
Tao Zhou
XWXiumin Wang
Xiumin Wang
Lei RenLei Ren
Lei Ren

23 June 2024
Verified
Conference Paper
Open access
JMJianan Mu
Jianan Mu
HHHusheng Han
Husheng Han
SSShangyi Shi
Shangyi Shi
JYJing Ye
Jing Ye
ZLZizhen Liu
Zizhen Liu
XLXiaowei Li
Xiaowei Li
The use of cross-scheme fully homomorphic encryption (FHE) in privacy-preserving applications present to be a new challenge to hardware accelerator design. Existing accelerator architectures with customized polynomial-level operator abstraction fail to efficiently handle hybrid FHE schemes due to the mismatch between computational demands and available hardware resources under various parameter settings. In this work, we propose a new accelerator architecture that consists of a novel finer-grained low-level operator, i.e., Meta-OP, that not only mathematically supports a diverse range of polynomial operations, but is also hardware-friendly for accelerator design without complex topological logic. We then design a new slot-based data management scheme to efficiently handle the distinct memory access patterns over the Meta-OP. With a slot-based data management approach, Alchemist can accelerate both arithmetic and logic FHE workloads with high hardware utilization rates. In the experiment, we show that Alchemist is up to 24,829X faster than CPU. For arithmetic FHE, compared with the SOTA ASIC accelerators, Alchemist achieves a 29.4X performance per area improvement on average. For logic FHE, compared with the SOTA ASIC accelerators, Alchemist achieves a 7.0X overall speed up on average.

24 August 2026
Verified
Book Chapter
Closed access
PDF file
XZXinyao Zheng
Xinyao Zheng
HHHusheng Han
Husheng Han
SSShangyi Shi
Shangyi Shi
QFQiyan Fang
Qiyan Fang
ZDZidong Du
Zidong Du
QGQi Guo
Qi Guo

29 November 2024 in arXiv
Verified
Preprint
Open access
PDF file
XZXinyao Zheng
Xinyao Zheng
HHHusheng Han
Husheng Han
SSShangyi Shi
Shangyi Shi
QFQiyan Fang
Qiyan Fang
ZDZidong Du
Zidong Du
QGQi Guo
Qi Guo
Large language models (LLMs) possess extensive knowledge and question-answering capabilities, having been widely deployed in privacy-sensitive domains like finance and medical consultation. During LLM inferences, cache-sharing methods are commonly employed to enhance efficiency by reusing cached states or responses for the same or similar inference requests. However, we identify that these cache mechanisms pose a risk of private input leakage, as the caching can result in observable variations in response times, making them a strong candidate for a timing-based attack hint. In this study, we propose a novel timing-based side-channel attack to execute input theft in LLMs inference. The cache-based attack faces the challenge of constructing candidate inputs in a large search space to hit and steal cached user queries. To address these challenges, we propose two primary components. The input constructor employs machine learning techniques and LLM-based approaches for vocabulary correlation learning while implementing optimized search mechanisms for generalized input construction. The time analyzer implements statistical time fitting with outlier elimination to identify cache hit patterns, continuously providing feedback to refine the constructor's search strategy. We conduct experiments across two cache mechanisms and the results demonstrate that our approach consistently attains high attack success rates in various applications. Our work highlights the security vulnerabilities associated with performance optimizations, underscoring the necessity of prioritizing privacy and security alongside enhancements in LLM inference.