Cover Image

Probing Privacy Leaks in LLM-based Code Generation via Test Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ge, Yifei, Chen, Zhenpeng, Sun, Weisong, Chen, Yuchen, Fang, Chunrong, Zhai, Juan, Zhang, Xiaofang, Feng, Xia, Liu, Yang, Chen, Zhenyu
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Security of Language Models for Code: A Systematic Literature Review
by: Chen, Yuchen, et al.
Published: (2024)

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
by: Xiao, Yuan, et al.
Published: (2025)

Demonstration Attack against In-Context Learning for Code Intelligence
by: Ge, Yifei, et al.
Published: (2024)

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
by: Xiao, Yuan, et al.
Published: (2026)

Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness
by: Sun, Weisong, et al.
Published: (2025)

Hybrid Privacy Policy-Code Consistency Check using Knowledge Graphs and LLMs
by: Mao, Zhenyu, et al.
Published: (2025)

Eliminating Backdoors in Neural Code Models for Secure Code Understanding
by: Sun, Weisong, et al.
Published: (2024)

Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
by: Yang, Guang, et al.
Published: (2026)

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code
by: Ning, Kaiwen, et al.
Published: (2024)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
by: Tessa, Melissa, et al.
Published: (2026)

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
by: Xu, Hanxiang, et al.
Published: (2024)

Verbatim Data Transcription Failures in LLM Code Generation: A State-Tracking Stress Test
by: Haque, Mohd Ariful, et al.
Published: (2026)

LeakGuard: Detecting Memory Leaks Accurately and Scalably
by: Liang, Hongliang, et al.
Published: (2025)

CodableLLM: Automating Decompiled and Source Code Mapping for LLM Dataset Generation
by: Manuel, Dylan, et al.
Published: (2025)

SAFuzz: Semantic-Guided Adaptive Fuzzing for LLM-Generated Code
by: Yang, Ziyi, et al.
Published: (2026)

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code
by: Elsayed, Mohamed, et al.
Published: (2026)

Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation
by: Lin, Bo, et al.
Published: (2025)

Repairing Leaks in Resource Wrappers
by: Malakar, Sanjay, et al.
Published: (2025)

Privacy Bills of Materials: A Transparent Privacy Information Inventory for Collaborative Privacy Notice Generation in Mobile App Development
by: Tao, Zhen, et al.
Published: (2025)

Towards Context-aware Mobile Privacy Notice: Implementation of A Deployable Contextual Privacy Policies Generator
by: Gong, Haochen, et al.
Published: (2025)

Generating API Parameter Security Rules with LLM for API Misuse Detection
by: Liu, Jinghua, et al.
Published: (2024)

Automated Generation of Accurate Privacy Captions From Android Source Code Using Large Language Models
by: Jain, Vijayanta, et al.
Published: (2026)

ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space
by: Chen, Chuyang, et al.
Published: (2025)

A First Look at Privacy Risks of Android Task-executable Voice Assistant Applications
by: Pan, Shidong, et al.
Published: (2025)

Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
by: Fu, Yujia, et al.
Published: (2023)

Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
by: Lin, Bo, et al.
Published: (2025)

Prompt Fuzzing for Fuzz Driver Generation
by: Lyu, Yunlong, et al.
Published: (2023)

Finding Privacy-relevant Source Code
by: Tang, Feiyang, et al.
Published: (2024)

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
by: Li, Yue, et al.
Published: (2026)

SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement
by: Chen, Yi, et al.
Published: (2026)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
by: Chen, Xuan, et al.
Published: (2026)

RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories
by: Wang, Yanlin, et al.
Published: (2026)

AutoDFBench 1.0: A Benchmarking Framework for Digital Forensic Tool Testing and Generated Code Evaluation
by: Wickramasekara, Akila, et al.
Published: (2025)

Towards Privacy-Preserving Code Generation: Differentially Private Code Language Models
by: Catal, Melih, et al.
Published: (2025)

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
by: Peng, Yibo, et al.
Published: (2025)

WildCode: An Empirical Analysis of Code Generated by ChatGPT
by: Khanmohammadi, Kobra, et al.
Published: (2025)

How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection
by: Chen, Maofei, et al.
Published: (2026)

FDI: Attack Neural Code Generation Systems through User Feedback Channel
by: Sun, Zhensu, et al.
Published: (2024)

SmartOracle: Generating Smart Contract Oracle via Fine-Grained Invariant Detection
by: Su, Jianzhong, et al.
Published: (2024)

Towards Precise Detection of Personal Information Leaks in Mobile Health Apps
by: Ardalani, Alireza, et al.
Published: (2024)