Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging

The enron corpus: a new dataset for email classification research

Bryan Klimt and Yiming Yang. 2004 · 2004

Earlier work this paper cites.

Language models are few-shot learners

Original

Tom B Brown. 2020 · 2005

Earlier work this paper cites.

Measuring catastrophic forgetting in neural networks

Ronald Kemker, Marc McClure, Angelina Abitino, Tyler Hayes, and Christopher Kanan. 2018 · 2018

Earlier work this paper cites.

Users really do answer telephone scams

Huahong Tu, Adam Doupé, Ziming Zhao, and Gail-Joon Ahn. 2019 · 2019

Earlier work this paper cites.

Extracting training data from large language models

Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021 · 2021

Earlier work this paper cites.

Lora: Low-rank adaptation of large language models

Original

Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021 · 2021

Earlier work this paper cites.

Editing models with task arithmetic

Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2022 · 2022

Earlier work this paper cites.

Dataless knowledge fusion by merging weights of language models

Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, and Pengxiang Cheng. 2022 · 2022

Earlier work this paper cites.

Memorization without overfitting: Analyzing the training dynamics of large language models

Kushal Tirumala, Aram Markosyan, Luke Zettlemoyer, and Armen Aghajanyan. 2022 · 2022

Earlier work this paper cites.

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al. 2022 · 2022

Earlier work this paper cites.

Qwen technical report

Original

Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023 · 2023

Earlier work this paper cites.

Quantifying memorization across neural language models

Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2023 · 2023

Earlier work this paper cites.

Jailbreaking black box large language models in twenty queries

Original

Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J Pappas, and Eric Wong. 2023 · 2023

Earlier work this paper cites.

Have you merged my model? on the robustness of large language model ip protection methods against model merging

Tianshuo Cong, Delong Ran, Zesen Liu, Xinlei He, Jinyuan Liu, Yichen Gong, Qi Li, Anyu Wang, and Xiaoyun Wang. 2023 · 2023

Earlier work this paper cites.

Tangent model composition for ensembling and continual fine-tuning

Tian Yu Liu and Stefano Soatto. 2023 · 2023

Earlier work this paper cites.

Analyzing leakage of personally identifiable information in language models

Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, and Santiago Zanella-Béguelin. 2023 · 2023

Earlier work this paper cites.

Scalable extraction of training data from (production) language models

Original

Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A Feder Cooper, Daphne Ippolito, Christopher A Choquette-Choo, Eric Wallace, Florian Tramèr, and Katherine Lee. 2023 · 2023

Earlier work this paper cites.

Direct preference optimization: Your language model is secretly a reward model

Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023 · 2023

Cited alongside, same era.

Large language model alignment: A survey

Original

Tianhao Shen, Renren Jin, Yufei Huang, Chuang Liu, Weilong Dong, Zishan Guo, Xinwei Wu, Yan Liu, and Deyi Xiong. 2023 · 2023

Cited alongside, same era.

Llama 2: Open foundation and fine-tuned chat models

Original

Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023 · 2023

Cited alongside, same era.

Aligning large language models with human: A survey

Original

Yufei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xingshan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, and Qun Liu. 2023 · 2023

Cited alongside, same era.

Model merging and safety alignment: One bad model spoils the bunch

Original

Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, and Mete Ozay. 2024 · 2024

Later among the works it cites.

Evaluating large language models’ capability to launch fully automated spear phishing campaigns: Validated on human subjects

Original

Fred Heiding, Simon Lermen, Andrew Kao, Bruce Schneier, and Arun Vishwanath. 2024 · 2024

Later among the works it cites.

Harmful fine-tuning attacks and defenses for large language models: A survey

Original

Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, and Ling Liu. 2024 · 2024

Later among the works it cites.

Alpaca against vicuna: Using llms to uncover memorization of llms

Original

Aly M Kassem, Omar Mahmoud, Niloofar Mireshghallah, Hyunwoo Kim, Yulia Tsvetkov, Yejin Choi, Sherif Saad, and Santu Rana. 2024 · 2024

Later among the works it cites.