Cover Image

Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Feiyang, Sun, Yuqiang, Zhang, Fan, Yang, Ziqi, Liu, Han, Liu, Yang
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning
by: Sun, Yuqiang, et al.
Published: (2024)

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

GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis
by: Sun, Yuqiang, et al.
Published: (2023)

Evaluating Large Language Models for Line-Level Vulnerability Localization
by: Zhang, Jian, et al.
Published: (2024)

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?
by: Fang, Chongzhou, et al.
Published: (2023)

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
by: Lingxiang, Wang, et al.
Published: (2025)

Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond
by: Gao, Zeyu, et al.
Published: (2025)

Smart Contract Fuzzing Towards Profitable Vulnerabilities
by: Kong, Ziqiao, et al.
Published: (2025)

Fine-Tuning LLMs for Code Mutation: A New Era of Cyber Threats
by: Setak, Mohammad, et al.
Published: (2024)

Fast and Accurate Silent Vulnerability Fix Retrieval
by: Liu, Xueqing, et al.
Published: (2025)

Towards Understanding and Characterizing Vulnerabilities in Intelligent Connected Vehicles through Real-World Exploits
by: Wang, Yuelin, et al.
Published: (2026)

Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
by: Yang, Chengran, et al.
Published: (2025)

Do Chase Your Tail! Missing Key Aspects Augmentation in Textual Vulnerability Descriptions of Long-tail Software through Feature Inference
by: Han, Linyi, et al.
Published: (2024)

Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models
by: Yang, Aidan Z. H., et al.
Published: (2024)

KernJC: Automated Vulnerable Environment Generation for Linux Kernel Vulnerabilities
by: Ruan, Bonan, et al.
Published: (2024)

An Empirical Study of Vulnerable Package Dependencies in LLM Repositories
by: Liu, Shuhan, et al.
Published: (2025)

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

VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities
by: Wang, Weizhe, et al.
Published: (2025)

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
by: Li, Yikun, et al.
Published: (2025)

Does the Vulnerability Threaten Our Projects? Automated Vulnerable API Detection for Third-Party Libraries
by: Zhang, Fangyuan, et al.
Published: (2024)

VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications
by: Zhu, Hao, et al.
Published: (2025)

Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking
by: Huang, Yifan, et al.
Published: (2025)

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery
by: Shafiuzzaman, Md, et al.
Published: (2026)

From Reviewers' Lens: Understanding Bug Bounty Report Invalid Reasons with LLMs
by: Zheng, Jiangrui, et al.
Published: (2025)

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
by: Yang, Hua, et al.
Published: (2025)

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

Transparency in App Analytics: Analyzing the Collection of User Interaction Data
by: Tang, Feiyang, et al.
Published: (2023)

PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
by: Wei, Zichao, et al.
Published: (2025)

Automated TEE Adaptation with LLMs: Identifying, Transforming, and Porting Sensitive Functions in Programs
by: Han, Ruidong, et al.
Published: (2025)

Exposing and Defending Membership Leakage in Vulnerability Prediction Models
by: Liao, Yihan, et al.
Published: (2025)

Fixing Security Vulnerabilities with AI in OSS-Fuzz
by: Zhang, Yuntong, et al.
Published: (2024)

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities
by: Li, Zhen, et al.
Published: (2024)

Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries
by: Zheng, Xinran, et al.
Published: (2026)

Characterizing Trust Boundary Vulnerabilities in TEE Containers: An Empirical Study
by: Liu, Weijie, et al.
Published: (2025)

Propagation-Based Vulnerability Impact Assessment for Software Supply Chains
by: Ruan, Bonan, et al.
Published: (2025)

Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems
by: Cao, Sicong, et al.
Published: (2024)

VERCATION: Precise Vulnerable Open-source Software Version Identification based on Static Analysis and LLM
by: Cheng, Yiran, et al.
Published: (2024)

MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs
by: Sun, Tiezhu, et al.
Published: (2025)

DLAP: A Deep Learning Augmented Large Language Model Prompting Framework for Software Vulnerability Detection
by: Yang, Yanjing, et al.
Published: (2024)

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
by: Han, Junxiao, et al.
Published: (2025)