Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs
Open Access
- 19 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3071-3085
Abstract
No abstract availableAll Related Versions
This publication has 20 references indexed in Scilit:
- Protecting Intellectual Property of Large Language Model-Based Code Generation APIs via Watermarks2023
- Poster: Membership Inference Attacks via Contrastive Learning2023
- Membership Inference Attacks Against Sequential Recommender Systems2023
- Membership Inference Attacks and Generalization2022
- ZeRO: Memory optimizations Toward Training Trillion Parameter Models2020
- Analyzing Information Leakage of Updates to Natural Language Models2020
- DeepSpeed2020
- Stealing Hyperparameters in Machine Learning2018
- Membership Inference Attacks Against Machine Learning Models2017
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016