Jieke Shi
5 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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).
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.
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.
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.
Papers
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…