Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers

Universal adversarial triggers for attacking and analyzing nlp

Original

Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh. 2019 · 1908

Earlier work this paper cites.

The bottom-up evolution of representations in the transformer: A study with machine translation and language modeling objectives

Original

Elena Voita, Rico Sennrich, and Ivan Titov. 2019 · 1909

Earlier work this paper cites.

How to share a secret

Adi Shamir. 1979 · 1979

Earlier work this paper cites.

Weight poisoning attacks on pre-trained models

Original

Keita Kurita, Paul Michel, and Graham Neubig. 2020 · 2004

Earlier work this paper cites.

Early exit optimizations for additive machine learned ranking systems

B Barla Cambazoglu, Hugo Zaragoza, Olivier Chapelle, Jiang Chen, Ciya Liao, Zhaohui Zheng, and Jon Degenhardt. 2010 · 2010

Earlier work this paper cites.

Branchynet: Fast inference via early exiting from deep neural networks

Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2016 · 2016

Earlier work this paper cites.

Badnets: Identifying vulnerabilities in the machine learning model supply chain

Original

Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg. 2017 · 2017

Earlier work this paper cites.

Probabilistic adaptive computation time

Michael Figurnov, Artem Sobolev, and Dmitry Vetrov. 2018 · 2018

Earlier work this paper cites.

Skipnet: Learning dynamic routing in convolutional networks

Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, and Joseph E Gonzalez. 2018 · 2018

Earlier work this paper cites.

Shallow-deep networks: Understanding and mitigating network overthinking

Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitras. 2019 · 2019

Earlier work this paper cites.

Language models are unsupervised multitask learners

Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019 · 2019

Earlier work this paper cites.

Strip: A defence against trojan attacks on deep neural networks

Original

Yansong Gao, Chang Xu, Derui Wang, Shiping Chen, Damith C. Ranasinghe, and Surya Nepal. 2020 · 2020

Earlier work this paper cites.

Autoprompt: Eliciting knowledge from language models with automatically generated prompts

Taylor Shin, Yasaman Razeghi, Robert L Logan IV, Eric Wallace, and Sameer Singh. 2020 · 2020

Earlier work this paper cites.

Mitigating backdoor attacks in LSTM-based text classification systems by backdoor keyword identification

Chuanshuai Chen and Jiazhu Dai. 2021 · 2021

Earlier work this paper cites.

Hidden backdoors in human-centric language models

Shaofeng Li, Hui Liu, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Haojin Zhu, and Jialiang Lu. 2021 · 2021

Earlier work this paper cites.

Anytime dense prediction with confidence adaptivity

Original

Zhuang Liu, Zhiqiu Xu, Hung-Ju Wang, Trevor Darrell, and Evan Shelhamer. 2021 · 2021

Earlier work this paper cites.

ONION: A simple and effective defense against textual backdoor attacks

Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2021b · 2021

Earlier work this paper cites.

Mind the style of text! adversarial and backdoor attacks based on text style transfer

Fanchao Qi, Yangyi Chen, Xurui Zhang, Mukai Li, Zhiyuan Liu, and Maosong Sun. 2021c · 2021

Earlier work this paper cites.

Multitask prompted training enables zero-shot task generalization

Original

Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al. 2021 · 2021

Earlier work this paper cites.

Finetuned language models are zero-shot learners

Original

Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021 · 2021

Earlier work this paper cites.

Rethinking stealthiness of backdoor attack against NLP models

Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, and Xu Sun. 2021 · 2021

Earlier work this paper cites.

Adavit: Adaptive tokens for efficient vision transformer

Original

Hongxu Yin, Arash Vahdat, Jose Alvarez, Arun Mallya, Jan Kautz, and Pavlo Molchanov. 2021 · 2021

Cited alongside, same era.

Training a helpful and harmless assistant with reinforcement learning from human feedback

Original

Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. 2022 · 2022

Cited alongside, same era.

A unified evaluation of textual backdoor learning: Frameworks and benchmarks

Ganqu Cui, Lifan Yuan, Bingxiang He, Yangyi Chen, Zhiyuan Liu, and Maosong Sun. 2022 · 2022

Cited alongside, same era.

Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space

Mor Geva, Avi Caciularu, Kevin Wang, and Yoav Goldberg. 2022 · 2022

Cited alongside, same era.

Large language models are zero-shot reasoners

Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022 · 2022

The alignment handbook

Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Shengyi Huang, Kashif Rasul, Alexander M. Rush, and Thomas Wolf. 2023 · 2023

Later among the works it cites.

Poisoning language models during instruction tuning

Alexander Wan, Eric Wallace, Sheng Shen, and Dan Klein. 2023 · 2023

Later among the works it cites.

Unicorn: A unified backdoor trigger inversion framework

Original

Zhenting Wang, Kai Mei, Juan Zhai, and Shiqing Ma. 2023 · 2023

Later among the works it cites.

Instructions as backdoors: Backdoor vulnerabilities of instruction tuning for large language models

Original

Jiashu Xu, Mingyu Derek Ma, Fei Wang, Chaowei Xiao, and Muhao Chen. 2023 · 2023

Later among the works it cites.

Backdooring instruction-tuned large language models with virtual prompt injection

Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, and Hongxia Jin. 2023 · 2023

Later among the works it cites.