Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jieke Shi

Jieke Shi

5 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Software Eng.×5Crypto×4AI×2Prog. Lang.×1

Frequent co-authors

David Lo5×
Zhou Yang3×
Junda He2×
Chengyan Ma2×
Ruidong Han2×
Ye Liu2×

Research Timeline

2026
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis

MemHint is a neuro-symbolic static analysis pipeline that significantly improves memory leak detection in C/C++ by combining LLM semantic understanding with Z3 symbolic reasoning, detecting more leaks than existing tools.

Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching

The paper introduces TEERepair, a framework that automatically repairs severe security vulnerabilities caused by improper partitioning in Trusted Execution Environments (TEEs) by combining a domain-specific language (DSL) with large language models (LLMs).

Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution

The paper introduces SymTEE, an LLM-assisted symbolic execution framework that detects missing input validation vulnerabilities in TEE applications without needing complex, real TEE setups.

Lossless Tensor Compression as Program Synthesis

Brevis compresses model checkpoints by synthesizing self-contained DSL programs that reconstruct tensors bit-exactly, reducing storage requirements and achieving high compression and decompression speeds.

Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering

This paper systematically investigates the effectiveness of LLM-as-a-Judge paradigm for evaluating Human-Oriented Binary Reverse Engineering (HOBRE) and introduces BinJudge, an adaptive evaluation scheme improving correlation with human experts and reducing API cost.

Highlighted terms show continued research focus across papers

Papers

cs.SEcs.AIcs.CREmpiricalRecentAug 7, 2026

Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering

Xiuwei Shang, Li Hu, Xiao Jiang, Jieke Shi +6 more

This paper systematically investigates the effectiveness of LLM-as-a-Judge paradigm for evaluating Human-Oriented Binary Reverse Engineering (HOBRE) and introduces BinJudge, an adaptive evaluation sch…

View →
cs.SEcs.AIcs.PLEmpirical
Recent
Aug 3, 2026

Lossless Tensor Compression as Program Synthesis

Jieke Shi, Junda He, Wenjia Jiang, Weifeng Sun +10 more

Brevis compresses model checkpoints by synthesizing self-contained DSL programs that reconstruct tensors bit-exactly, reducing storage requirements and achieving high compression and decompression spe…

View →
cs.SEcs.CRMay 21, 2026

Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching

Chengyan Ma, Jieke Shi, Ruidong Han, Ye Liu +3 more

The paper introduces TEERepair, a framework that automatically repairs severe security vulnerabilities caused by improper partitioning in Trusted Execution Environments (TEEs) by combining a domain-sp…

View →
cs.SEcs.CRMay 21, 2026

Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution

Chengyan Ma, Jieke Shi, Ruidong Han, Ye Liu +2 more

The paper introduces SymTEE, an LLM-assisted symbolic execution framework that detects missing input validation vulnerabilities in TEE applications without needing complex, real TEE setups.

View →
cs.SEcs.CRMar 28, 2026

Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis

Huihui Huang, Jieke Shi, Bo Wang, Zhou Yang +1 more

MemHint is a neuro-symbolic static analysis pipeline that significantly improves memory leak detection in C/C++ by combining LLM semantic understanding with Z3 symbolic reasoning, detecting more leaks…

View →