Fetching the paper…
Reading the bibliography…
To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by obfuscating the true intentions behind user prompts.This approach compels LLMs to inadvertently generate restricted content, bypassing their built-in content security measures.
Generating natural language adversarial examples
Moustafa Alzantot, Yash Sharma, Ahmed Elgohary, Bo-Jhang Ho, Mani Srivastava, and Kai-Wei Chang · 2018
Earlier work this paper cites.
Generating natural language adversarial examples through probability weighted word saliency
Shuhuai Ren, Yihe Deng, Kun He, and Wanxiang Che · 2019
Earlier work this paper cites.
Language models are few-shot learners
Ben Mann, N Ryder, M Subbiah, J Kaplan, P Dhariwal, A Neelakantan, P Shyam, G Sastry, A Askell, S Agarwal, et al · 2020
Earlier work this paper cites.
Adversarial glue: A multi-task benchmark for robustness evaluation of language models
Boxin Wang, Chejian Xu, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, and Bo Li · 2021
Earlier work this paper cites.
Content policy, 2022
Inc Openai · 2022
Earlier work this paper cites.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al · 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
Earlier work this paper cites.
Improving alignment of dialogue agents via targeted human judgements
Amelia Glaese, Nat McAleese, Maja Trębacz, John Aslanides, Vlad Firoiu, Timo Ewalds, Maribeth Rauh, Laura Weidinger, Martin Chadwick, Phoebe Thacker, et al · 2022
Earlier work this paper cites.
Red-teaming the stable diffusion safety filter
Javier Rando, Daniel Paleka, David Lindner, Lennart Heim, and Florian Tramèr · 2022
Earlier work this paper cites.
Red teaming language models with language models
Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, and Geoffrey Irving · 2022
Earlier work this paper cites.
What is the size of the training set for gpt-3, 2023
Abcarter · 2023
Earlier work this paper cites.
Prompting4debugging: Red-teaming text-to-image diffusion models by finding problematic prompts
Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen, and Wei-Chen Chiu · 2023
Earlier work this paper cites.
Ratgpt: Turning online llms into proxies for malware attacks
Mika Beckerich, Laura Plein, and Sergio Coronado · 2023
Earlier work this paper cites.
Large language models can be used to effectively scale spear phishing campaigns
Julian Hazell · 2023
Earlier work this paper cites.
A first look at toxicity injection attacks on open-domain chatbots
Connor Weeks, Aravind Cheruvu, Sifat Muhammad Abdullah, Shravya Kanchi, Daphne Yao, and Bimal Viswanath · 2023
Cited alongside, same era.
Understanding multi-turn toxic behaviors in open-domain chatbots
Bocheng Chen, Guangjing Wang, Hanqing Guo, Yuanda Wang, and Qiben Yan · 2023
Cited alongside, same era.
Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang · 2023
Cited alongside, same era.
Role play with large language models
Murray Shanahan, Kyle McDonell, and Laria Reynolds · 2023
Cited alongside, same era.
Multi-step jailbreaking privacy attacks on chatgpt
Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, and Yangqiu Song · 2023
Cited alongside, same era.
Assert: Automated safety scenario red teaming for evaluating the robustness of large language models
Alex Mei, Sharon Levy, and William Yang Wang · 2023
Later among the works it cites.
Flirt: Feedback loop in-context red teaming
Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, and Rahul Gupta · 2023
Later among the works it cites.
Smoothllm: Defending large language models against jailbreaking attacks
Alexander Robey, Eric Wong, Hamed Hassani, and George J Pappas · 2023
Later among the works it cites.
Query-efficient black-box red teaming via bayesian optimization
Deokjae Lee, JunYeong Lee, Jung-Woo Ha, Jin-Hwa Kim, Sang-Woo Lee, Hwaran Lee, and Hyun Oh Song · 2023
Later among the works it cites.
Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson · 2023
Cited alongside, same era.
jailbreakchat
Alexalbert · 2023
Cited alongside, same era.
Huan Ma, Changqing Zhang, Huazhu Fu, Peilin Zhao, and Bingzhe Wu · 2023
Cited alongside, same era.
Pretraining language models with human preferences
Tomasz Korbak, Kejian Shi, Angelica Chen, Rasika Vinayak Bhalerao, Christopher Buckley, Jason Phang, Samuel R Bowman, and Ethan Perez · 2023
Cited alongside, same era.
Dongyu Yao, Jianshu Zhang, Ian G Harris, and Marcel Carlsson · 2023
Cited alongside, same era.
From chatgpt to threatgpt: Impact of generative ai in cybersecurity and privacy
Maanak Gupta, CharanKumar Akiri, Kshitiz Aryal, Eli Parker, and Lopamudra Praharaj · 2023
Cited alongside, same era.
Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts
Jiahao Yu, Xingwei Lin, and Xinyu Xing · 2023
Cited alongside, same era.
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, and Mario Fritz · 2023
Later among the works it cites.
Red-teaming large language models using chain of utterances for safety-alignment
Rishabh Bhardwaj and Soujanya Poria · 2023
Later among the works it cites.
Prompt packer: Deceiving llms through compositional instruction with hidden attacks
Shuyu Jiang, Xingshu Chen, and Rui Tang · 2023
Later among the works it cites.
Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al · 2023
Later among the works it cites.
Baichuan 2: Open large-scale language models
Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, Fan Yang, et al · 2023
Later among the works it cites.
Jade: A linguistics-based safety evaluation platform for llm, 2023
Mi Zhang, Xudong Pan, and Min Yang · 2023
Later among the works it cites.
Jailbroken: How does llm safety training fail?
Alexander Wei, Nika Haghtalab, and Jacob Steinhardt · 2024
Closest in time.
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
Closest in time.
Drattack: Prompt decomposition and reconstruction makes powerful llm jailbreakers
Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, and Cho-Jui Hsieh · 2024
Closest in time.