SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios
Paper • 2509.22097 • Published • 3
Jieke SHI
jiekeshi
AI & ML interests
None yet
Recent Activity
authored a paper 3 days ago
Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models authored a paper 3 days ago
Greening Large Language Models of CodeOrganizations
None yet
upvoted a paper 2 days ago
authored 19
papers 3 days ago
Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models
Paper • 2310.01166 • Published
Greening Large Language Models of Code
Paper • 2309.04076 • Published
Unveiling Memorization in Code Models
Paper • 2308.09932 • Published
What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues
Paper • 2303.09795 • Published
Prioritizing Speech Test Cases
Paper • 2302.00330 • Published
Stealthy Backdoor Attack for Code Models
Paper • 2301.02496 • Published
Lossless Tensor Compression as Program Synthesis
Paper • 2608.02162 • Published • 11
PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing
Paper • 2601.06910 • Published
Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
Paper • 2602.06751 • Published
ESG Reporting Lifecycle Management with Large Language Models and AI Agents
Paper • 2603.10646 • Published
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis
Paper • 2603.27224 • Published
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
Paper • 2604.02665 • Published
Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
Paper • 2604.08083 • Published
Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching
Paper • 2605.22087 • Published
Finding Missing Input Validation in TEEs via LLM-Assisted Symbolic Execution
Paper • 2605.22058 • Published
From Code to Courtroom: LLMs as the New Software Judges
Paper • 2503.02246 • Published
Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
Paper • 2503.14838 • Published
Back to the Basics: Rethinking Issue-Commit Linking with LLM-Assisted Retrieval
Paper • 2507.09199 • Published
SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents
Paper • 2507.18957 • Published