Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach

• URL: http://arxiv.org/abs/2512.07814v2
• Date: Tue, 09 Dec 2025 03:23:33 GMT
• Title: Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach
• Authors: Hua Yang, Alejandro Velasco, Sen Fang, Bowen Xu, Denys Poshyvanyk,
• Abstract summary: 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.
• Score: 58.05800140178267
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns due to their reliance on open-source repositories containing abundant personally identifiable information (PII). Prior work shows that commercial models can reproduce sensitive PII, yet existing studies largely treat PII as a single category and overlook the heterogeneous risks among different types. We investigate whether distinct PII types vary in their likelihood of being learned and leaked by LLM4Code, and whether this relationship is causal. Our methodology includes building a dataset with diverse PII types, fine-tuning representative models of different scales, computing training dynamics on real PII data, and formulating a structural causal model to estimate the causal effect of learnability on leakage. Results show that leakage risks differ substantially across PII types and correlate with their training dynamics: easy-to-learn instances such as IP addresses exhibit higher leakage, while harder types such as keys and passwords leak less frequently. Ambiguous types show mixed behaviors. This work provides the first causal evidence that leakage risks are type-dependent and offers guidance for developing type-aware and learnability-aware defenses for LLM4Code.

Related papers

• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• 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)
• How Quantization Impacts Privacy Risk on LLMs for Code? [8.607910400111853]
  We conduct the first empirical study on how quantization influences task performance and privacy risk simultaneously in LLMs4Code.<n>Our results demonstrate that quantization has a significant impact on reducing the privacy risk relative to the original model.<n>We also uncover a positive correlation between task performance and privacy risk, indicating an underlying tradeoff.
  arXiv  Detail & Related papers  (2025-07-31T19:28:31Z)
• When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning [9.660010886245155]
  This paper systematically investigates the privacy threats posed by membership inference attacks (MIAs) targeting encoder models.<n>We propose a novel membership inference attack method based on the p-norm of feature vectors, termed the Embedding Lp-Norm Likelihood Attack (LpLA)
  arXiv  Detail & Related papers  (2025-06-06T05:03:29Z)
• Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning [4.275908952997288]
  Federated Learning (FL) is a collaborative learning framework designed to protect client data.<n>Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to model extraction attacks.<n>This paper examines the vulnerability of FL-based victim models to two types of model extraction attacks.
  arXiv  Detail & Related papers  (2025-05-25T22:40:10Z)
• 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)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• An Empirical Study of Deep Learning Models for Vulnerability Detection [4.243592852049963]
  We surveyed and reproduced 9 state-of-the-art deep learning models on 2 widely used vulnerability detection datasets. We investigated model capabilities, training data, and model interpretation. Our findings can help better understand model results, provide guidance on preparing training data, and improve the robustness of the models.
  arXiv  Detail & Related papers  (2022-12-15T19:49:34Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)

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.