A Small Leak Sinks All: Exploring the Transferable Vulnerability of Source Code Models

• URL: http://arxiv.org/abs/2511.08127v1
• Date: Wed, 12 Nov 2025 01:41:20 GMT
• Title: A Small Leak Sinks All: Exploring the Transferable Vulnerability of Source Code Models
• Abstract summary: This work systematically studies the intrinsic vulnerability transferability of both traditional SCMs and LLM4Code.<n>We design HABITAT, consisting of a tailored perturbation-inserting mechanism and a hierarchical Reinforcement framework.<n>Our constructed adversarial examples crafted based on traditional SCMs achieve up to 64% success rates against LLM4Code, surpassing the state-of-the-art by over 15%.
• Score: 1.2320871858014988
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Source Code Model learn the proper embeddings from source codes, demonstrating significant success in various software engineering or security tasks. The recent explosive development of LLM extends the family of SCMs,bringing LLMs for code that revolutionize development workflows. Investigating different kinds of SCM vulnerability is the cornerstone for the security and trustworthiness of AI-powered software ecosystems, however, the fundamental one, transferable vulnerability, remains critically underexplored. Existing studies neither offer practical ways, i.e. require access to the downstream classifier of SCMs, to produce effective adversarial samples for adversarial defense, nor give heed to the widely used LLM4Code in modern software development platforms and cloud-based integrated development environments. Therefore, this work systematically studies the intrinsic vulnerability transferability of both traditional SCMs and LLM4Code, and proposes a victim-agnostic approach to generate practical adversarial samples. We design HABITAT, consisting of a tailored perturbation-inserting mechanism and a hierarchical Reinforcement Learning framework that adaptively selects optimal perturbations without requiring any access to the downstream classifier of SCMs. Furthermore, an intrinsic transferability analysis of SCM vulnerabilities is conducted, revealing the potential vulnerability correlation between traditional SCMs and LLM4Code, together with fundamental factors that govern the success rate of victim-agnostic transfer attacks. These findings of SCM vulnerabilities underscore the critical focal points for developing robust defenses in the future. Experimental evaluation demonstrates that our constructed adversarial examples crafted based on traditional SCMs achieve up to 64% success rates against LLM4Code, surpassing the state-of-the-art by over 15%.

Related papers

• Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability [65.56750741053266]
  Large language models (LLMs) have transformed misinformation from a content-centric problem into a broader ecosystem-level security challenge.<n>In this paper, we introduce a role-layer framework to unify these risks and defenses.<n>The role characterizes LLMs as attackers, defenders, and vulnerable components of verification systems, while the layer dimension covers content, social contexts, evidence environments, and verification.
  arXiv  Detail & Related papers  (2026-07-11T17:04:17Z)
• Secure Coding Drift in LLM-Assisted Post-Quantum Cryptography Development: A Gamified Fix [0.0]
  Large language models (LLMs) are heavily embedded in software development.<n>LLMs generate insecure or suboptimal code, particularly in security critical domains.<n>This paper introduces Secure Coding Drift in PQC, a novel socio technical vulnerability model.
  arXiv  Detail & Related papers  (2026-06-17T18:10:10Z)
• Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model [60.60587869092729]
  Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment.<n>We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation.
  arXiv  Detail & Related papers  (2026-02-07T07:42:07Z)
• CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents [12.097503515854141]
  CoTDeceptor is the first adversarial code obfuscation framework targeting CoT-enhanced LLM detectors.<n>Our findings highlight potential risks in real-world software supply chains.
  arXiv  Detail & Related papers  (2025-12-24T15:55:42Z)
• Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization [51.12422886183246]
  Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks.<n>Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the dynamic interplay between evolving threats and safeguards in real-world web contexts.<n>We propose ACE-Safety, a novel framework that jointly optimize attack and defense models by seamlessly integrating two key innovative procedures.
  arXiv  Detail & Related papers  (2025-11-24T15:23:41Z)
• Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence [15.881854286231997]
  Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats.<n>In this paper, we investigate the intrinsic vulnerabilities of LLMs in cyber threat intelligence (CTI)<n>We introduce a novel categorization methodology that integrates stratification, autoregressive refinement, and human-in-the-loop supervision.
  arXiv  Detail & Related papers  (2025-09-28T02:08:27Z)
• Ensembling Large Language Models for Code Vulnerability Detection: An Empirical Evaluation [69.8237598448941]
  This study investigates the potential of ensemble learning to enhance the performance of Large Language Models (LLMs) in source code vulnerability detection.<n>We propose Dynamic Gated Stacking (DGS), a Stacking variant tailored for vulnerability detection.
  arXiv  Detail & Related papers  (2025-09-16T03:48:22Z)
• Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation [16.29310628754089]
  Large Language Models (LLMs) have become powerful tools for automated code generation.<n>LLMs often overlook critical security practices, which can result in the generation of insecure code.<n>This paper examines their inherent tendencies to produce insecure code, their capability to generate secure code when guided by self-generated vulnerability hints, and their effectiveness in repairing vulnerabilities when provided with different levels of feedback.
  arXiv  Detail & Related papers  (2025-06-28T23:24:33Z)
• LLM-BSCVM: An LLM-Based Blockchain Smart Contract Vulnerability Management Framework [5.88442044992561]
  LLM-BSCVM is a Large Language Model-based smart contract vulnerability management framework.<n>It provides end-to-end vulnerability detection, analysis, repair, and evaluation capabilities for Web 3.0 ecosystem.<n>It achieves a vulnerability detection accuracy and F1 score exceeding 91% on benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-23T03:05:09Z)
• A Trustworthy Multi-LLM Network: Challenges,Solutions, and A Use Case [59.58213261128626]
  We propose a blockchain-enabled collaborative framework that connects multiple Large Language Models (LLMs) into a Trustworthy Multi-LLM Network (MultiLLMN)<n>This architecture enables the cooperative evaluation and selection of the most reliable and high-quality responses to complex network optimization problems.
  arXiv  Detail & Related papers  (2025-05-06T05:32:46Z)
• SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models [50.34706204154244]
  Acquiring reasoning capabilities catastrophically degrades inherited safety alignment.<n>Certain scenarios suffer 25 times higher attack rates.<n>Despite tight reasoning-answer safety coupling, MLRMs demonstrate nascent self-correction.
  arXiv  Detail & Related papers  (2025-04-09T06:53:23Z)
• An Empirical Study of Automated Vulnerability Localization with Large Language Models [21.84971967029474]
  Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in vulnerability localization remains underexplored. Our investigation encompasses 10+ leading LLMs suitable for code analysis, including ChatGPT and various open-source models. We explore the efficacy of these LLMs using 4 distinct paradigms: zero-shot learning, one-shot learning, discriminative fine-tuning, and generative fine-tuning.
  arXiv  Detail & Related papers  (2024-03-30T08:42:10Z)
• Data Poisoning for In-context Learning [49.77204165250528]
  In-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks.<n>This paper delves into the critical issue of ICL's susceptibility to data poisoning attacks.<n>We introduce ICLPoison, a specialized attacking framework conceived to exploit the learning mechanisms of ICL.
  arXiv  Detail & Related papers  (2024-02-03T14:20:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.