Fetching the paper…
Reading the bibliography…
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API.
A review of false data injection attacks against modern power systems
Gaoqi Liang, Junhua Zhao, Fengji Luo, Steven R Weller, and Zhao Yang Dong · 2016
Earlier work this paper cites.
Jack Bandy and Nicholas Vincent · 2021
Earlier work this paper cites.
Measuring massive multitask language understanding
Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt · 2021
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.
Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned
Deep Ganguli, Liane Lovitt, Jackson Kernion, Amanda Askell, Yuntao Bai, Saurav Kadavath, Ben Mann, Ethan Perez, Nicholas Schiefer, Kamal Ndousse, 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, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe · 2022
Earlier work this paper cites.
Cross site scripting (XSS), 2022
OWASP · 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.
Ignore previous prompt: Attack techniques for language models
Fábio Perez and Ian Ribeiro · 2022
Earlier work this paper cites.
Taxonomy of risks posed by language models
Laura Weidinger, Jonathan Uesato, Maribeth Rauh, Conor Griffin, Po-Sen Huang, John Mellor, Amelia Glaese, Myra Cheng, Borja Balle, Atoosa Kasirzadeh, et al · 2022
Earlier work this paper cites.
Not what you’ve signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection
Sahar Abdelnabi, Kai Greshake, Shailesh Mishra, Christoph Endres, Thorsten Holz, and Mario Fritz · 2023
Earlier work this paper cites.
Rohan Anil, Andrew M. Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, et al · 2023
Earlier work this paper cites.
Fine-tuning the GPT 3.5 Turbo: A Python code deep dive, Oct 2023
Mohamed Azharudeen · 2023
Earlier work this paper cites.
Explore, establish, exploit: Red teaming language models from scratch
Stephen Casper, Jason Lin, Joe Kwon, Gatlen Culp, and Dylan Hadfield-Menell · 2023
Cited alongside, same era.
A survey on evaluation of large language models
Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Kaijie Zhu, Hao Chen, Linyi Yang, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, et al · 2023
Cited alongside, same era.
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks, 2023
Samyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Edward Grefenstette, Tim Rocktäschel, and David Scott Krueger · 2023
Cited alongside, same era.
BeaverTails: Towards improved safety alignment of LLM via a human-preference dataset
Jiaming Ji, Mickel Liu, Juntao Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, and Yaodong Yang · 2023
Cited alongside, same era.
A causal framework for AI regulation and auditing
Lee Sharkey, Clíodhna Ní Ghuidhir, Dan Braun, Jérémy Scheurer, Mikita Balesni, Lucius Bushnaq, Charlotte Stix, and Marius Hobbhahn · 2023
Closest in time.
Towards understanding sycophancy in language models
Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R Johnston, et al · 2023
Closest in time.
Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang · 2023
Closest in time.
AI model GPT-3 (dis)informs us better than humans
Giovanni Spitale, Nikola Biller-Andorno, and Federico Germani · 2023
Closest in time.
Stanford Alpaca: An instruction-following LLaMA model
Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto · 2023
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, and Hang Li · 2023
Cited alongside, same era.
The Operational Risks of AI in Large-Scale Biological Attacks: A Red-Team Approach
Christopher A. Mouton, Caleb Lucas, and Ella Guest · 2023
Cited alongside, same era.
A systematic review of detection and prevention techniques of SQL injection attacks
Mohammed Nasereddin, Ashaar ALKhamaiseh, Malik Qasaimeh, and Raad Al-Qassas · 2023
Cited alongside, same era.
In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the python exec method
National Institute of Standards and Technology · 2023
Cited alongside, same era.
SQL injection vulnerability in langchain before v0.0.247 allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component
National Institute of Standards and Technology · 2023
Cited alongside, same era.
An issue in langchain v.0.0.199 allows an attacker to execute arbitrary code via the PALChain in the python exec method
National Institute of Standards and Technology · 2023
Cited alongside, same era.
ChatGPT’s new code interpreter has giant security hole, allows hackers to steal your data
Avram Piltch · 2023
Cited alongside, same era.
Fine-tuning aligned language models compromises safety, even when users do not intend to!
Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson · 2023
Cited alongside, same era.
Closest in time.
Llama 2: Open foundation and fine-tuned chat models
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al · 2023
Closest in time.
Aligning large language models with human: A survey
Yufei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xingshan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, and Qun Liu · 2023
Closest in time.
Shadow alignment: The ease of subverting safely-aligned language models
Xianjun Yang, Xiao Wang, Qi Zhang, Linda Petzold, William Yang Wang, Xun Zhao, and Dahua Lin · 2023
Closest in time.
Low-resource languages jailbreak GPT-4
Zheng-Xin Yong, Cristina Menghini, and Stephen H Bach · 2023
Closest in time.
Removing RLHF protections in GPT-4 via fine-tuning
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, and Daniel Kang · 2023
Closest in time.
Synthetic lies: Understanding AI-generated misinformation and evaluating algorithmic and human solutions
Jiawei Zhou, Yixuan Zhang, Qianni Luo, Andrea G Parker, and Munmun De Choudhury · 2023
Closest in time.
Universal and transferable adversarial attacks on aligned language models
Andy Zou, Zifan Wang, J. Zico Kolter, and Matt Fredrikson · 2023
Closest in time.