MoPe: Model Perturbation-based Privacy Attacks on Language Models

MoPe: Model Perturbation-based Privacy Attacks on Language Models

22 October 2023

Marvin Li

Jeffrey G. Wang

Papers citing "MoPe: Model Perturbation-based Privacy Attacks on Language Models"

8 / 8 papers shown

Title
The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text Matthieu Meeus Lukas Wutschitz Santiago Zanella Béguelin Shruti Tople Reza Shokri 75 0 0 24 Feb 2025
Blind Baselines Beat Membership Inference Attacks for Foundation Models Debeshee Das Jie Zhang Florian Tramèr MIALM 72 28 1 23 Jun 2024
Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4 Bishwas Mandal G. Amariucai Shuangqing Wei 19 1 0 07 Apr 2024
Knowledge Unlearning for Mitigating Privacy Risks in Language Models Joel Jang Dongkeun Yoon Sohee Yang Sungmin Cha Moontae Lee Lajanugen Logeswaran Minjoon Seo KELM PILM MU 145 110 0 04 Oct 2022
How BPE Affects Memorization in Transformers Eugene Kharitonov Marco Baroni Dieuwke Hupkes 161 31 0 06 Oct 2021
Deduplicating Training Data Makes Language Models Better Katherine Lee Daphne Ippolito A. Nystrom Chiyuan Zhang Douglas Eck Chris Callison-Burch Nicholas Carlini SyDa 237 588 0 14 Jul 2021
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe ... Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy AIMat 245 1,977 0 31 Dec 2020
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 267 1,798 0 14 Dec 2020