Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation

• URL: http://arxiv.org/abs/2503.22760v1
• Date: Thu, 27 Mar 2025 16:09:23 GMT
• Title: Malicious and Unintentional Disclosure Risks in Large Language Models for Code Generation
• Abstract summary: This paper explores the risk that a large language model (LLM) trained for code generation will generate content that discloses sensitive information included in its training data.<n>We decompose this risk into two components: unintentional disclosure and malicious disclosure.<n>We describe methods to assess unintentional and malicious disclosure risks side-by-side across different releases of training datasets and models.
• Score: 2.94944680995069
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data. We decompose this risk, known in the literature as ``unintended memorization,'' into two components: unintentional disclosure (where an LLM presents secrets to users without the user seeking them out) and malicious disclosure (where an LLM presents secrets to an attacker equipped with partial knowledge of the training data). We observe that while existing work mostly anticipates malicious disclosure, unintentional disclosure is also a concern. We describe methods to assess unintentional and malicious disclosure risks side-by-side across different releases of training datasets and models. We demonstrate these methods through an independent assessment of the Open Language Model (OLMo) family of models and its Dolma training datasets. Our results show, first, that changes in data source and processing are associated with substantial changes in unintended memorization risk; second, that the same set of operational changes may increase one risk while mitigating another; and, third, that the risk of disclosing sensitive information varies not only by prompt strategies or test datasets but also by the types of sensitive information. These contributions rely on data mining to enable greater privacy and security testing required for the LLM training data supply chain.

Related papers

• Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges [55.425628316813174]
  Multi-modal Large Language Models (MLLMs) process both text and images.<n>Compared to text-only models, MLLMs can extract and expose sensitive information embedded in images.<n>Some MLLMs are susceptible to privacy breaches, leaking sensitive data embedded in images or stored in memory.
  arXiv  Detail & Related papers  (2026-06-08T07:19:42Z)
• Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach [58.05800140178267]
  Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns.<n>We investigate whether distinct PII types vary in their likelihood of being learned and leaked by LLM4Code.<n>Results show that leakage risks differ substantially across PII types and correlate with their training dynamics.<n>This work provides the first causal evidence that leakage risks are type-dependent and offers guidance for developing type-aware and learnability-aware defenses.
  arXiv  Detail & Related papers  (2025-12-08T18:47:40Z)
• RAG Security and Privacy: Formalizing the Threat Model and Attack Surface [4.823988025629304]
  Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce more accurate and grounded responses.<n>Existing research has demonstrated that RAGs can leak sensitive information through training data memorization or adversarial prompts, and RAG systems inherit many of these vulnerabilities.<n>Despite these risks, there is currently no formal framework that defines the threat landscape for RAG systems.
  arXiv  Detail & Related papers  (2025-09-24T17:11:35Z)
• Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning [50.45435841411193]
  Code Language Models (CLMs) exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted.<n>We introduce CodeEraser, an advanced variant that selectively unlearns sensitive memorized segments in code while preserving the structural integrity and functional correctness of the surrounding code.
  arXiv  Detail & Related papers  (2025-09-17T07:12:35Z)
• Differential Privacy in Machine Learning: From Symbolic AI to LLMs [49.1574468325115]
  Differential privacy provides a formal framework to mitigate privacy risks.<n>It ensures that the inclusion or exclusion of any single data point does not significantly alter the output of an algorithm.
  arXiv  Detail & Related papers  (2025-06-13T11:30:35Z)
• Breaking the Gold Standard: Extracting Forgotten Data under Exact Unlearning in Large Language Models [26.5039481643457]
  We introduce a novel data extraction attack that compromises even exact unlearning.<n>We demonstrate our attack's effectiveness on a simulated medical diagnosis dataset.
  arXiv  Detail & Related papers  (2025-05-30T09:09:33Z)
• Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning [5.974072640812041]
  Large Language Models for Code (LLMs4Code) excel at code generation tasks, yielding promise to release developers from huge software development burdens.<n>These models have been shown to suffer from the significant privacy risks due to the potential leakage of sensitive information embedded during training.<n>Machine unlearning has emerged as a promising solution by enabling models to "forget" sensitive information without full retraining.
  arXiv  Detail & Related papers  (2025-02-09T01:50:34Z)
• On the Privacy Risk of In-context Learning [36.633860818454984]
  We show that deploying prompted models presents a significant privacy risk for the data used within the prompt. We also observe that the privacy risk of prompted models exceeds fine-tuned models at the same utility levels.
  arXiv  Detail & Related papers  (2024-11-15T17:11:42Z)
• Extracting Unlearned Information from LLMs with Activation Steering [46.16882599881247]
  Unlearning has emerged as a solution to remove sensitive knowledge from models after training. We propose activation steering as a method for exact information retrieval from unlearned models. Our results demonstrate that exact information retrieval from unlearned models is possible, highlighting a severe vulnerability of current unlearning techniques.
  arXiv  Detail & Related papers  (2024-11-04T21:42:56Z)
• Extracting Memorized Training Data via Decomposition [24.198975804570072]
  We demonstrate a simple, query-based decompositional method to extract news articles from two frontier Large Language Models. We extract at least one sentence from 73 articles, and over 20% of verbatim sentences from 6 articles. If replicable at scale, this training data extraction methodology could expose new LLM security and safety vulnerabilities.
  arXiv  Detail & Related papers  (2024-09-18T23:59:32Z)
• LLM-PBE: Assessing Data Privacy in Large Language Models [111.58198436835036]
  Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Despite the critical nature of this issue, there has been no existing literature to offer a comprehensive assessment of data privacy risks in LLMs. Our paper introduces LLM-PBE, a toolkit crafted specifically for the systematic evaluation of data privacy risks in LLMs.
  arXiv  Detail & Related papers  (2024-08-23T01:37:29Z)
• "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
  Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
  arXiv  Detail & Related papers  (2024-06-26T05:36:23Z)
• REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space [35.61862064581971]
  Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns.<n>We propose REVS, a novel non-gradient-based method for unlearning sensitive information from LMs.
  arXiv  Detail & Related papers  (2024-06-13T17:02:32Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks [65.21536453075275]
  We focus on the summarization task and investigate the membership inference (MI) attack. We exploit text similarity and the model's resistance to document modifications as potential MI signals. We discuss several safeguards for training summarization models to protect against MI attacks and discuss the inherent trade-off between privacy and utility.
  arXiv  Detail & Related papers  (2023-10-20T05:44:39Z)
• Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs [59.596335292426105]
  This paper collects the first open-source dataset to evaluate safeguards in large language models. We train several BERT-like classifiers to achieve results comparable with GPT-4 on automatic safety evaluation.
  arXiv  Detail & Related papers  (2023-08-25T14:02:12Z)

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.