Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation

The use of confidence or fiducial limits illustrated in the case of the binomial

Charles J Clopper and Egon S Pearson · 1934

Earlier work this paper cites.

Pushing Boundaries or Crossing Lines? The Complex Ethics of ChatGPT Jailbreaking

Anja Boxleitner · 2023

Earlier work this paper cites.

Figstep: Jailbreaking large vision-language models via typographic visual prompts

Original

Yichen Gong, Delong Ran, Jinyuan Liu, Conglei Wang, Tianshuo Cong, Anyu Wang, Sisi Duan, and Xiaoyun Wang · 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

Earlier work this paper cites.

Contextual manipulations in adversarial prompting

L. Zhang et al · 2023

Earlier work this paper cites.

Defensive strategies against ai jailbreaking: Challenges and innovations

J. Li and R. Chen · 2023

Earlier work this paper cites.

Defending ChatGPT against jailbreak attack via self-reminders

Yueqi Xie, Jingwei Yi, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, and Fangzhao Wu · 2023

Earlier work this paper cites.

Self-guard: Empower the llm to safeguard itself

Original

Zezhong Wang, Fangkai Yang, Lu Wang, Pu Zhao, Hongru Wang, Liang Chen, Qingwei Lin, and Kam-Fai Wong · 2023

Earlier work this paper cites.

Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

Rao Abhinav, Vashistha S., Naik Atharva, Aditya Somak, and Choudhury Monojit · 2023

Cited alongside, same era.

Ai control: Improving safety despite intentional subversion

Original

Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, and Fabien Roger · 2023

Cited alongside, same era.

Automatic jailbreaking of the text-to-image generative ai systems

Original

Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, and Sung Ju Hwang · 2024

Cited alongside, same era.

Jailbreakzoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models

Original

Haibo Jin, Leyang Hu, Xinuo Li, Peiyan Zhang, Chonghan Chen, Jun Zhuang, and Haohan Wang · 2024

Cited alongside, same era.

Don’t listen to me: Understanding and exploring jailbreak prompts of large language models

Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models

Original

Liwei Jiang, Kavel Rao, Seungju Han, Allyson Ettinger, Faeze Brahman, Sachin Kumar, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi, et al · 2024

Later among the works it cites.

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

Later among the works it cites.

Best-of-n jailbreaking

Original

John Hughes, Sara Price, Aengus Lynch, Rylan Schaeffer, Fazl Barez, Sanmi Koyejo, Henry Sleight, Erik Jones, Ethan Perez, and Mrinank Sharma · 2024

Later among the works it cites.

Improving alignment and robustness with circuit breakers

Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, J Zico Kolter, Matt Fredrikson, and Dan Hendrycks · 2024

Later among the works it cites.