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

Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model not to restate PII. We study such direct, inference-time PII leakage using a model-agnostic framework that (i) defines leakage as risk-weighted, token-level events across 11 PII types, (ii) traces leakage curves as a function of the allowed CoT budget, and (iii) compares open- and closed-source model families on a structured PII dataset with a hierarchical risk taxonomy. We find that CoT consistently elevates leakage, especially for high-risk categories, and that leakage is strongly family- and budget-dependent. Increasing the reasoning budget can either amplify or attenuate leakage depending on the base model. We then benchmark lightweight inference-time gatekeepers: a rule-based detector, a TF-IDF + logistic regression classifier, a GLiNER-based NER model, and an LLM-as-judge, using risk-weighted F1, Macro-F1, and recall. No single method dominates across models or budgets, motivating hybrid, style-adaptive gatekeeping policies that balance utility and risk under a common, reproducible protocol.

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that identifies universal activation directions: latent directions in a model's residual stream whose linear addition at inference time consistently increases the likelihood of generating PII across prompts. These model-specific directions generalize across contexts and amplify PII generation probability, with minimal impact on generation quality. UniLeak recovers such directions without access to training data or groundtruth PII, relying only on self-generated text. Across multiple models and datasets, steering along these universal directions substantially increases PII leakage compared to existing prompt-based extraction methods. Our results offer a new perspective on PII leakage: the superposition of a latent signal in the model's representations, enabling both risk amplification and mitigation.

The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning (ML) models using available code quickly. The training data for ML models, often regarded as private property (e.g., clinical records, transaction information), is at significant risk of information leakage. Property Inference Attacks (PIAs), as a significant type of privacy attack, aim to expose global property information of the training set. In this paper, we present Code-Poisoning Property Inference Attack (CPPIA), the first code-level PIA, which overcomes four limitations of existing works: insufficient attack performance, severe degradation of model accuracy, high computational overhead, and failure under defenses. We consider malicious code providers from code hosting platforms (GitHub) and coding agents (Codex). Upon downloading the poisoned code, data holders train models with their private data without professional auditing, subsequently releasing label-only APIs to the public. The adversary embeds the properties into secret samples during training and queries the trained model on these samples later to leak privacy. CPPIA offers 100% attack accuracy without degrading model accuracy. It is also computationally lightweight and requires no shadow models. We evaluate the attack performance across four datasets, eight model architectures, eighteen properties, and under three defense mechanisms, demonstrating the universality and effectiveness of CPPIA.