Copertina

Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yuanheng, Chen, Zhuoyang, Liu, Xiaoyun, Wang, Yuhao, Liu, Mingwei, Shi, Yang, Huang, Kaifeng, Zhao, Shengjie
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Semantics Over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities
di: Huang, Qiqing, et al.
Pubblicazione: (2026)

Cryptanalysis of Pseudorandom Error-Correcting Codes
di: Wang, Tianrui, et al.
Pubblicazione: (2025)

Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environments
di: Chen, Congcong, et al.
Pubblicazione: (2025)

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs
di: Li, Yue, et al.
Pubblicazione: (2025)

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
di: Ying, Zonghao, et al.
Pubblicazione: (2026)

HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation
di: Chen, Qirui, et al.
Pubblicazione: (2026)

Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness
di: Yang, Peiru, et al.
Pubblicazione: (2025)

Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs
di: Liu, Honghao, et al.
Pubblicazione: (2026)

Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective
di: Chen, Meifang, et al.
Pubblicazione: (2026)

Conditional Cube Attack on Round-Reduced ASCON
di: Li, Zheng, et al.
Pubblicazione: (2025)

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

A Cascade Approach for APT Campaign Attribution in System Event Logs: Technique Hunting and Subgraph Matching
di: Huang, Yi-Ting, et al.
Pubblicazione: (2024)

The Illusion of Anonymity: Uncovering the Impact of User Actions on Privacy in Web3 Social Ecosystems
di: Wang, Bin, et al.
Pubblicazione: (2024)

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
di: Zhang, Shuoming, et al.
Pubblicazione: (2025)

An Approach for Handling Missing Attribute Values in Attribute-Based Access Control Policy Mining
di: Bui, Thang, et al.
Pubblicazione: (2025)

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
di: Li, Yuxi, et al.
Pubblicazione: (2024)

MalGuard: Towards Real-Time, Accurate, and Actionable Detection of Malicious Packages in PyPI Ecosystem
di: Gao, Xingan, et al.
Pubblicazione: (2025)

Understanding the Security Risks of Decentralized Exchanges by Uncovering Unfair Trades in the Wild
di: Chen, Jiaqi, et al.
Pubblicazione: (2024)

PrivCode: When Code Generation Meets Differential Privacy
di: Liu, Zheng, et al.
Pubblicazione: (2025)

How Does Naming Affect LLMs on Code Analysis Tasks?
di: Wang, Zhilong, et al.
Pubblicazione: (2023)

Uncovering CWE-CVE-CPE Relations with Threat Knowledge Graphs
di: Shi, Zhenpeng, et al.
Pubblicazione: (2023)

DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
di: Chen, Yuchen, et al.
Pubblicazione: (2026)

Who Moved My Transaction? Uncovering Post-Transaction Auditability Vulnerabilities in Modern Super Apps
di: Liu, Junlin, et al.
Pubblicazione: (2025)

I Can Tell Your Secrets: Inferring Privacy Attributes from Mini-app Interaction History in Super-apps
di: Cai, Yifeng, et al.
Pubblicazione: (2025)

The Midas Touch: Triggering the Capability of LLMs for RM-API Misuse Detection
di: Yang, Yi, et al.
Pubblicazione: (2024)

Uncover the Premeditated Attacks: Detecting Exploitable Reentrancy Vulnerabilities by Identifying Attacker Contracts
di: Yang, Shuo, et al.
Pubblicazione: (2024)

Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation
di: Liu, Shangqing, et al.
Pubblicazione: (2024)

From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses
di: Meng, Xiangtao, et al.
Pubblicazione: (2025)

Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption
di: Liu, Xuanqi, et al.
Pubblicazione: (2024)

Quantization Aware Attack: Enhancing Transferable Adversarial Attacks by Model Quantization
di: Yang, Yulong, et al.
Pubblicazione: (2023)

Uncovering Software-Based Power Side-Channel Attacks on Apple M1/M2 Systems
di: Chawla, Nikhil, et al.
Pubblicazione: (2023)

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
di: Chen, Yanzuo, et al.
Pubblicazione: (2023)

PrintListener: Uncovering the Vulnerability of Fingerprint Authentication via the Finger Friction Sound
di: Zhou, Man, et al.
Pubblicazione: (2024)

Decentralized Multi-Authority Attribute-Based Inner-Product Functional Encryption: Noisy and Evasive Constructions from Lattices
di: Liu, Jiaqi, et al.
Pubblicazione: (2025)

Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators
di: Li, Xitao, et al.
Pubblicazione: (2025)

ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs
di: Yang, Yuchen, et al.
Pubblicazione: (2024)

ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts
di: Zhang, Lyuye, et al.
Pubblicazione: (2024)

CLIProv: A Contrastive Log-to-Intelligence Multimodal Approach for Threat Detection and Provenance Analysis
di: Li, Jingwen, et al.
Pubblicazione: (2025)

Unveiling the Attribute Misbinding Threat in Identity-Preserving Models
di: Fu, Junming, et al.
Pubblicazione: (2025)

KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis
di: Liu, Zhijie, et al.
Pubblicazione: (2025)