The paper introduces a framework for collusion between train- and inference-time adversaries in ML pipelines, proposes a guideline for conjecturing collusion potential, explains prior work, and empirically validates five cases.
Measuring non-adversarial repro- duction of training data in large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs show high memorization capability under prefix attacks but low propensity under generic or dataset-specific prompts, with continual pre-training further reducing both.
citing papers explorer
-
SoK: Colluding Adversaries in Machine Learning Pipelines
The paper introduces a framework for collusion between train- and inference-time adversaries in ML pipelines, proposes a guideline for conjecturing collusion potential, explains prior work, and empirically validates five cases.
-
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
LLMs show high memorization capability under prefix attacks but low propensity under generic or dataset-specific prompts, with continual pre-training further reducing both.