all AI news
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships
Feb. 20, 2024, 5:43 a.m. | Myung Gyo Oh, Hong Eun Ahn, Leo Hyun Park, Taekyoung Kwon
cs.LG updates on arXiv.org arxiv.org
Abstract: Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of the original training data. This strategy differs from prior studies by aiming to intensify the LM's retention of its pre-training dataset. To achieve this, the attacker needs to collect generated texts that are closely aligned with the pre-training data. However, without …
abstract amplify arxiv attacks cs.cl cs.cr cs.lg data data extraction extraction fine-tuning language language models lms novel paper prior strategy studies through training training data type vulnerable
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Analyst (Digital Business Analyst)
@ Activate Interactive Pte Ltd | Singapore, Central Singapore, Singapore