Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

• URL: http://arxiv.org/abs/2603.17174v1
• Date: Tue, 17 Mar 2026 22:08:45 GMT
• Title: Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
• Abstract summary: Code generation large language models (LLMs) are increasingly integrated into modern software development.<n>Existing scanning approaches rely on token-level generation consistency to invert attack targets.<n>We present CodeScan, which is the first poisoning-scanning framework tailored to code generation models.
• Score: 12.405265138053329
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backdoor and poisoning attacks that induce the generation of insecure code, yet effective defenses remain limited. Existing scanning approaches rely on token-level generation consistency to invert attack targets, which is ineffective for source code where identical semantics can appear in diverse syntactic forms. We present CodeScan, which, to the best of our knowledge, is the first poisoning-scanning framework tailored to code generation models. CodeScan identifies attack targets by analyzing structural similarities across multiple generations conditioned on different clean prompts. It combines iterative divergence analysis with abstract syntax tree (AST)-based normalization to abstract away surface-level variation and unify semantically equivalent code, isolating structures that recur consistently across generations. CodeScan then applies LLM-based vulnerability analysis to determine whether the extracted structures contain security vulnerabilities and flags the model as compromised when such a structure is found. We evaluate CodeScan against four representative attacks under both backdoor and poisoning settings across three real-world vulnerability classes. Experiments on 108 models spanning three architectures and multiple model sizes demonstrate 97%+ detection accuracy with substantially lower false positives than prior methods.

Related papers

• MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents [74.64265314956441]
  We propose a unified black-box attack framework that poisons graph-structured external memory with coordinated text-image evidence.<n>MemVenom achieves strong end-to-end attack success with minimal impact on benign performance, reaching up to 99.15% on GPT-5-family web agents.
  arXiv  Detail & Related papers  (2026-06-09T11:53:25Z)
• EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy [66.59724477993339]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks.<n>We propose EntropyScan, a lightweight and trigger-agnostic method for model-level backdoor detection in LVLMs.<n>Our code will be publicly available soon.
  arXiv  Detail & Related papers  (2026-05-15T08:01:32Z)
• CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents [27.35968236632966]
  LLM-based code interpreter agents are increasingly deployed in critical situations.<n>Existing benchmarks fail to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context.<n>We introduce CIBER, an automated benchmark that combines dynamic attack generation, isolated secure sandboxing, and state-aware evaluation.
  arXiv  Detail & Related papers  (2026-02-23T06:41:41Z)
• SecureScan: An AI-Driven Multi-Layer Framework for Malware and Phishing Detection Using Logistic Regression and Threat Intelligence Integration [0.0]
  This work presents SecureScan, an AI-driven, triplelayer detection framework.<n>It integrates logistic regression-based classification, analysis, and external threat intelligence via the VirusTotal API.<n>On benchmark datasets, SecureScan achieves 93.1 percent accuracy with balanced precision.
  arXiv  Detail & Related papers  (2026-02-11T11:26:11Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• Detecting Stealthy Data Poisoning Attacks in AI Code Generators [1.1371178703578924]
  We present a systematic study on the effectiveness of existing poisoning detection methods under a stealthy threat model.<n>We perform targeted poisoning on three DL models (CodeBERT, CodeT5+, AST-T5), and evaluate spectral signatures analysis, activation clustering, and static analysis as defenses.<n>Our results show that all methods struggle to detect triggerless poisoning, with representation-based approaches failing to isolate poisoned samples and static analysis suffering false positives and false negatives.
  arXiv  Detail & Related papers  (2025-08-29T14:00:06Z)
• Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets [8.977790462534152]
  We propose DePA, a novel line-level detection and cleansing method tailored to the structural properties of code.<n>DePA significantly outperforms existing methods, achieving 0.14-0.19 improvement in detection F1-score and a 44-65% increase in poisoned segment localization precision.
  arXiv  Detail & Related papers  (2025-02-27T16:30:00Z)
• Reformulation is All You Need: Addressing Malicious Text Features in DNNs [53.45564571192014]
  We propose a unified and adaptive defense framework that is effective against both adversarial and backdoor attacks.<n>Our framework outperforms existing sample-oriented defense baselines across a diverse range of malicious textual features.
  arXiv  Detail & Related papers  (2025-02-02T03:39:43Z)
• An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection [17.948513691133037]
  We introduce CodeBreaker, a pioneering LLM-assisted backdoor attack framework on code completion models. By integrating malicious payloads directly into the source code with minimal transformation, CodeBreaker challenges current security measures.
  arXiv  Detail & Related papers  (2024-06-10T22:10:05Z)
• Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks [15.531860128240385]
  This work investigates novel techniques for transitioning backdoors from the AI/ML domain to traditional computer malware.<n>We present MalInstructCoder, a framework designed to assess the cybersecurity vulnerabilities of instruction-tuned Code LLMs.<n>We conduct a comprehensive investigation into the exploitability of the code-specific instruction tuning process involving three state-of-the-art Code LLMs.
  arXiv  Detail & Related papers  (2024-04-29T10:14:58Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)
• Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection [67.53296659361598]
  adversarial EXEmples can bypass machine learning-based detection by perturbing relatively few input bytes. We develop a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section.
  arXiv  Detail & Related papers  (2020-08-17T07:16:57Z)
• Scalable Backdoor Detection in Neural Networks [61.39635364047679]
  Deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch. We propose a novel trigger reverse-engineering based approach whose computational complexity does not scale with the number of labels, and is based on a measure that is both interpretable and universal across different network and patch types. In experiments, we observe that our method achieves a perfect score in separating Trojaned models from pure models, which is an improvement over the current state-of-the art method.
  arXiv  Detail & Related papers  (2020-06-10T04:12:53Z)

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.