Guofeng Qin

Guofeng Qin

Auto-generated profile, based on publicly available information

Guofeng Qin

The School of Cyber Science and Technology, Shandong University, Qingdao, China; Quan Cheng Laboratory, Jinan, China

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
24 October 2023 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
LLLu Li
Lu Li
GQGuofeng Qin
Guofeng Qin
YYYang Yu
Yang Yu
WWWeijia Wang
Weijia Wang
Kyber is the only post-quantum cryptography (PQC) key encapsulation mechanism in the National Institute of Standards and Technology PQC project. This brief investigates the design of compact instruction set extensions (ISEs) for Kyber. We focus on implementing number-theoretic transform (NTT) and propose a hardware design of the modular multiplication based on an optimized $k^{2}$ -reduction. Compared to other works, our design is more compact since the optimized $k^{2}$ -reduction comprises multiplications with significantly smaller multipliers than Montgomery reduction and Barrett reduction. Then, we integrate the $k^{2}$ -reduction into an instruction for the butterfly transformation. We also propose auxiliary instructions that can switch the half words between two registers to facilitate the rearranging coefficients in NTT. To showcase the advantage of the instructions, we implement the ISEs in a chip design for the Hummingbird E203 core. Compared to the software implementation on RISC-V with assembly code, our co-design implementations for NTT show a speedup by a factor of 2.6. Besides, the area overhead is 93 LUTs and 1 DSP without any additional resources of FFs and RAMs using Artix-7 FPGA, which is more compact than previous software–hardware co-designs of Kyber.

18 March 2024 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
LLLu Li
Lu Li
QTQi Tian
Qi Tian
GQGuofeng Qin
Guofeng Qin
SCShuaiyu Chen
Shuaiyu Chen
WWWeijia Wang
Weijia Wang
Post-quantum cryptography is considered to provide security against both traditional and quantum computer attacks. Dilithium is a digital signature algorithm that derives its security from the challenge of finding short vectors in lattices. It has been selected as one of the standardizations in the NIST post-quantum cryptography project. Hardware-software co-design is a commonly adopted implementation strategy to address various implementation challenges, including limited resources, high performance, and flexibility requirements. In this study, we investigate using compact instruction set extensions (ISEs) for Dilithium, aiming to improve software efficiency with low hardware overheads. To begin with, we propose tightly coupled accelerators that are deeply integrated into the RISC-V processor. These accelerators target the most computationally demanding components in resource-constrained processors, such as polynomial generation, Number Theoretic Transform (NTT), and modular arithmetic. Next, we design a set of custom instructions that seamlessly integrate with the RISC-V base instruction formats, completing the accelerators in a compact manner. Subsequently, we implement our ISEs in a chip design for the Hummingbird E203 core and conduct performance benchmarks for Dilithium utilizing these ISEs. Additionally, we evaluate the resource consumption of the ISEs on FPGA and ASIC technologies. Compared to the reference software implementation on the RISC-V core, our co-design demonstrates a remarkable speedup factor ranging from 6.95 to 9.96. This significant improvement in performance is achieved by incorporating additional hardware resources, specifically, a 35% increase in LUTs, a 14% increase in FFs, 7 additional DSPs, and no additional RAM. Furthermore, compared to the state-of-the-art approach, our work achieves faster speed performance with a reduced circuit cost. Specifically, the usage of additional LUTs, FFs, and RAMs is reduced by 47.53%, 50.43%, and 100%, respectively. On ASIC technology, our approach demonstrates 12, 412 cell counts. Our co-design provides a better tradeoff implementation on speed performance and circuit overheads.

10 October 2023 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
JZJiayun Zhou
Jiayun Zhou
GQGuofeng Qin
Guofeng Qin
LLLu Li
Lu Li
CGChun Guo
Chun Guo
WWWeijia Wang
Weijia Wang
Shuffling is a time-randomized countermeasure against side-channel attacks. To achieve effective protections, shuffling is usually combined with other countermeasures, such as the masking. It requires the shuffling to be as efficient as possible. In this work, we describe an instruction set extensions (ISEs) for shuffling countermeasure. Our ISEs focuses on the generation of random permutations, which is the most difficult part to deploy the shuffling in microprocessors. The Thorp shuffling is implemented in hardware, enabling the instruction to generate random permutations. We design new ISEs compatible to the RISC-V standard instruction set format. Then, we present applications of our ISEs by giving two combinations of shuffling and masking, which can be regarded as promising software–hardware co-designs of side-channel countermeasures. At last, we embed the ISEs to the RISC-V core called tinyriscv, and evaluate the silicon overhead and the side-channel security of the shuffled masked AND operation. The evaluation shows that the new instruction can significantly improve the security of masking countermeasures.