A Causal Perspective on the Role of Training Dynamics for Interpreting Privacy Risks in Code Models

The paper investigates how different types of personally identifiable information (PII) are learned and leaked by large language models for code (LLM4Code). By creating a diverse PII dataset, fine‑tuning models of various scales, and analyzing training dynamics through a structural causal model, the authors find that leakage risk varies by PII type—easy‑to‑learn data such as IP addresses leak more often, while harder types like keys and passwords leak less. The study provides causal evidence that leakage risks are type‑dependent and suggests that defenses should be tailored to specific PII categories and their learnability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• fine-tuning
• safety