AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

Linguistic regularities in continuous space word representations

Tomáš Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013 · 2013

Earlier work this paper cites.

Pytorch: An imperative style, high-performance deep learning library

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019 · 2019

Earlier work this paper cites.

A general language assistant as a laboratory for alignment

Original

Amanda Askell, Yuntao Bai, Anna Chen, Dawn Drain, Deep Ganguli, Tom Henighan, Andy Jones, Nicholas Joseph, Ben Mann, Nova DasSarma, et al. 2021 · 2021

Earlier work this paper cites.

The trojan detection challenge

Mantas Mazeika, Dan Hendrycks, Huichen Li, Xiaojun Xu, Sidney Hough, Andy Zou, Arezoo Rajabi, Qi Yao, Zihao Wang, Jian Tian, et al. 2023 · 2022

Earlier work this paper cites.

Training language models to follow instructions with human feedback

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022 · 2022

Earlier work this paper cites.

Diff-in-means concept editing is worst-case optimal: Explaining a result by sam marks and max tegmark, 2023

Nora Belrose. 2023 · 2023

Earlier work this paper cites.

Jailbreaking black box large language models in twenty queries

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

Earlier work this paper cites.

Jailbreaker: Automated jailbreak across multiple large language model chatbots

Original

Gelei Deng, Yi Liu, Yuekang Li, Kailong Wang, Ying Zhang, Zefeng Li, Haoyu Wang, Tianwei Zhang, and Yang Liu. 2023 · 2023

Earlier work this paper cites.

Automatically auditing large language models via discrete optimization

Erik Jones, Anca Dragan, Aditi Raghunathan, and Jacob Steinhardt. 2023 · 2023

Earlier work this paper cites.

Multi-step jailbreaking privacy attacks on chatgpt

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, and Yangqiu Song. 2023a · 2023

Earlier work this paper cites.

Autodan: Generating stealthy jailbreak prompts on aligned large language models

Original

Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao. 2023 · 2023

Earlier work this paper cites.

Steering llama 2 via contrastive activation addition

Original

Nina Panickssery, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Matt Turner. 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

Earlier work this paper cites.

Jailbreak in pieces: Compositional adversarial attacks on multi-modal language models

Erfan Shayegani, Yue Dong, and Nael Abu-Ghazaleh. 2023 · 2023

Earlier work this paper cites.

Activation addition: Steering language models without optimization

Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J Vazquez, Ulisse Mini, and Monte MacDiarmid. 2023 · 2023

Earlier work this paper cites.

Large language model unlearning

Yuanshun Yao, Xiaojun Xu, and Yang Liu. 2023 · 2023

Earlier work this paper cites.

Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts

Original

Jiahao Yu, Xingwei Lin, and Xinyu Xing. 2023 · 2023

Earlier work this paper cites.

Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher

Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. 2023 · 2023

Earlier work this paper cites.

Refusal in language models is mediated by a single direction

Original

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, and Neel Nanda. 2024 · 2024

Cited alongside, same era.

Towards inference-time category-wise safety steering for large language models

Amrita Bhattacharjee, Shaona Ghosh, Traian Rebedea, and Christopher Parisien. 2024 · 2024

Cited alongside, same era.

Are aligned neural networks adversarially aligned?

Nicholas Carlini, Milad Nasr, Christopher A Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei W Koh, Daphne Ippolito, Florian Tramer, and Ludwig Schmidt. 2024 · 2024

Cited alongside, same era.

Jailbreakbench: An open robustness benchmark for jailbreaking large language models

Original

Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J Pappas, Florian Tramer, et al. 2024 · 2024

Cited alongside, same era.

Or-bench: An over-refusal benchmark for large language models

Data advisor: Dynamic data curation for safety alignment of large language models

Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, and Aram Galstyan. 2024a · 2024

Later among the works it cites.

SafeDecoding: Defending against jailbreak attacks via safety-aware decoding

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, and Radha Poovendran. 2024 · 2024

Later among the works it cites.

Qwen2. 5 technical report

Original

An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2024 · 2024

Later among the works it cites.

Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher

Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. 2024 · 2024

Later among the works it cites.

Safe unlearning: A surprisingly effective and generalizable solution to defend against jailbreak attacks

Original

Zhexin Zhang, Junxiao Yang, Pei Ke, Shiyao Cui, Chujie Zheng, Hongning Wang, and Minlie Huang. 2024 · 2024