BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Tabor: A highly accurate approach to inspecting and restoring trojan backdoors in ai systems

Original

Wenbo Guo, Lun Wang, Xinyu Xing, Min Du, and Dawn Song. 2019 · 1908

Earlier work this paper cites.

Realtoxicityprompts: Evaluating neural toxic degeneration in language models

Original

Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A Smith. 2020 · 2009

Earlier work this paper cites.

Concealed data poisoning attacks on nlp models

Original

Eric Wallace, Tony Z Zhao, Shi Feng, and Sameer Singh. 2020 · 2010

Earlier work this paper cites.

Onion: A simple and effective defense against textual backdoor attacks

Original

Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2020 · 2011

Earlier work this paper cites.

An alternative softmax operator for reinforcement learning

Kavosh Asadi and Michael L Littman. 2017 · 2017

Earlier work this paper cites.

Deep reinforcement learning from human preferences

Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017 · 2017

Earlier work this paper cites.

Fine-pruning: Defending against backdooring attacks on deep neural networks

Kang Liu, Brendan Dolan-Gavitt, and Siddharth Garg. 2018 · 2018

Earlier work this paper cites.

Strip: A defence against trojan attacks on deep neural networks

Yansong Gao, Change Xu, Derui Wang, Shiping Chen, Damith C. Ranasinghe, and Surya Nepal. 2019 · 2019

Earlier work this paper cites.

Neural cleanse: Identifying and mitigating backdoor attacks in neural networks

Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal Viswanath, Haitao Zheng, and Ben Y Zhao. 2019 · 2019

Earlier work this paper cites.

Neural attention distillation: Erasing backdoor triggers from deep neural networks

Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, and Xingjun Ma. 2020 · 2020

Earlier work this paper cites.

{ \{ T-Miner } \} : A generative approach to defend against trojan attacks on { \{ DNN-based } \} text classification

Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed, Neal Mangaokar, Jiameng Pu, Mobin Javed, Chandan K Reddy, and Bimal Viswanath. 2021 · 2021

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.

Adaspeech: Adaptive text to speech for custom voice

Original

Mingjian Chen, Xu Tan, Bohan Li, Yanqing Liu, Tao Qin, Sheng Zhao, and Tie-Yan Liu. 2021 · 2021

Earlier work this paper cites.

Design and evaluation of a multi-domain trojan detection method on deep neural networks

Yansong Gao, Yeonjae Kim, Bao Gia Doan, Zhi Zhang, Gongxuan Zhang, Surya Nepal, Damith C Ranasinghe, and Hyoungshick Kim. 2021 · 2021

Earlier work this paper cites.

Rap: Robustness-aware perturbations for defending against backdoor attacks on nlp models

Original

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

Earlier work this paper cites.

Spinning language models: Risks of propaganda-as-a-service and countermeasures

Eugene Bagdasaryan and Vitaly Shmatikov. 2022 · 2022

Earlier work this paper cites.

Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned

Original

Deep Ganguli, Liane Lovitt, Jackson Kernion, Amanda Askell, Yuntao Bai, Saurav Kadavath, Ben Mann, Ethan Perez, Nicholas Schiefer, Kamal Ndousse, et al. 2022 · 2022

Earlier work this paper cites.

Asleep at the keyboard? assessing the security of github copilot’s code contributions

Hammond Pearce, Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, and Ramesh Karri. 2022 · 2022

Earlier work this paper cites.

Red teaming language models with language models

Original

Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, and Geoffrey Irving. 2022 · 2022

Earlier work this paper cites.

Constrained optimization with dynamic bound-scaling for effective nlp backdoor defense

Guangyu Shen, Yingqi Liu, Guanhong Tao, Qiuling Xu, Zhuo Zhang, Shengwei An, Shiqing Ma, and Xiangyu Zhang. 2022 · 2022

Cited alongside, same era.

Rethinking the reverse-engineering of trojan triggers

Zhenting Wang, Kai Mei, Hailun Ding, Juan Zhai, and Shiqing Ma. 2022 · 2022

Cited alongside, same era.

Post-training detection of backdoor attacks for two-class and multi-attack scenarios

Original

Zhen Xiang, David J Miller, and George Kesidis. 2022 · 2022

Cited alongside, same era.

Adversarial unlearning of backdoors via implicit hypergradient

Yi Zeng, Si Chen, Won Park, Zhuoqing Mao, Ming Jin, and Ruoxi Jia. 2022 · 2022

Cited alongside, same era.

Fine-mixing: Mitigating backdoors in fine-tuned language models

Zhiyuan Zhang, Lingjuan Lyu, Xingjun Ma, Chenguang Wang, and Xu Sun. 2022 · 2022

Cited alongside, same era.

Decodingtrust: A comprehensive assessment of trustworthiness in gpt models

Original

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, et al. 2023 · 2023

Later among the works it cites.

Shadow alignment: The ease of subverting safely-aligned language models

Original

Xianjun Yang, Xiao Wang, Qi Zhang, Linda Petzold, William Yang Wang, Xun Zhao, and Dahua Lin. 2023 · 2023

Later among the works it cites.

Lmsys-chat-1m: A large-scale real-world llm conversation dataset

Original

Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Tianle Li, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zhuohan Li, Zi Lin, Eric Xing, et al. 2023 · 2023

Later among the works it cites.

Universal and transferable adversarial attacks on aligned language models

Original

Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson. 2023b · 2023

Later among the works it cites.