GuardEmb: Dynamic Watermark for Safeguarding Large Language Model Embedding Service Against Model Stealing Attack
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 7518-7534
Abstract
Liaoyaqi Wang, Minhao Cheng. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.Keywords
This publication has 19 references indexed in Scilit:
- The Stable Signature: Rooting Watermarks in Latent Diffusion Models2023
- Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor AttacksMachine Intelligence Research, 2023
- Towards Data-Free Model Stealing in a Hard Label Setting2022
- REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data2021
- Model Extraction Attacks and Defenses on Cloud-Based Machine Learning ModelsIEEE Communications Magazine, 2020
- Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data2018
- Protecting Intellectual Property of Deep Neural Networks with Watermarking2018
- Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures2015
- Evasion Attacks against Machine Learning at Test Time2013
- Basic Message Coding2008