Fetching the paper…
Reading the bibliography…
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on.
Sard: A software assurance reference dataset, 1970
Paul Black · 1970
Earlier work this paper cites.
Secure computer system: Unified exposition and multics interpretation
David E Bell, Leonard J La Padula, et al · 1976
Earlier work this paper cites.
A lattice model of secure information flow
Dorothy E Denning · 1976
Earlier work this paper cites.
Security policies and security models
Joseph A Goguen and José Meseguer · 1982
Earlier work this paper cites.
Department of Defense Trusted Computer System Evaluation Criteria
United States. Department of Defense · 1987
Earlier work this paper cites.
Access control: principle and practice
Ravi S Sandhu and Pierangela Samarati · 1994
Earlier work this paper cites.
X. 509 internet public key infrastructure online certificate status protocol-ocsp
Michael Myers, Rich Ankney, Ambarish Malpani, Slava Galperin, and Carlisle Adams · 1999
Earlier work this paper cites.
Secure program partitioning
Steve Zdancewic, Lantian Zheng, Nathaniel Nystrom, and Andrew C Myers · 2002
Earlier work this paper cites.
Language-based information-flow security
Andrei Sabelfeld and Andrew C Myers · 2003
Earlier work this paper cites.
Using replication and partitioning to build secure distributed systems
Lantian Zheng, Stephen Chong, Andrew C Myers, and Steve Zdancewic · 2003
Earlier work this paper cites.
Markdown: Syntax
John Gruber · 2012
Earlier work this paper cites.
A language for automatically enforcing privacy policies
Jean Yang, Kuat Yessenov, and Armando Solar-Lezama · 2012
Earlier work this paper cites.
Language models are unsupervised multitask learners
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al · 2019
Earlier work this paper cites.
Stolen memories: Leveraging model memorization for calibrated { \{ White-Box } \} membership inference
Klas Leino and Matt Fredrikson · 2020
Earlier work this paper cites.
Compositional security for reentrant applications
Ethan Cecchetti, Siqiu Yao, Haobin Ni, and Andrew C Myers · 2021
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
Earlier work this paper cites.
Examining zero-shot vulnerability repair with large language models
Hammond Pearce, Benjamin Tan, Baleegh Ahmad, Ramesh Karri, and Brendan Dolan-Gavitt · 2022
Earlier work this paper cites.
Ignore Previous Prompt: Attack Techniques For Language Models, November 2022
Fábio Perez and Ian Ribeiro · 2022
Earlier work this paper cites.
https://www.bing.com/chat , 2023
Bing Chat · 2023
Earlier work this paper cites.
https://chat.openai.com/g/g-alKfVrz9K-canva , 2023
Canva GPT · 2023
Earlier work this paper cites.
https://www.aidocmaker.com/ , 2023
DocMaker ChatGPT Plugin · 2023
Cited alongside, same era.
https://github.com/features/copilot , 2023
Github Copilot - Your AI pair programmer · 2023
Cited alongside, same era.
https://images.google.com/ , 2023
Google images · 2023
Cited alongside, same era.
https://twitter.com/imrat/status/1726317710945235003 , 2023
GPTs Statistic Data · 2023
Cited alongside, same era.
https://openai.com/blog/introducing-gpts , 2023
GPTs Store · 2023
Cited alongside, same era.
https://openai.com/blog/chatgpt , 2023
Introducting ChatGPT · 2023
Cited alongside, same era.
https://openai.com/blog/new-models-and-developer-products-announced-at-devday, 2023
Prompt Injection attack against LLM-integrated Applications, June 2023
Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, and Yang Liu · 2023
Later among the works it cites.
Prompt Injection Attacks and Defenses in LLM-Integrated Applications, October 2023
Yupei Liu, Yuqi Jia, Runpeng Geng, Jinyuan Jia, and Neil Zhenqiang Gong · 2023
Later among the works it cites.
Rodrigo Pedro, Daniel Castro, Paulo Carreira, and Nuno Santos · 2023
Later among the works it cites.
Smoothllm: Defending large language models against jailbreaking attacks, 2023
Alexander Robey, Eric Wong, Hamed Hassani, and George J. Pappas · 2023
Later among the works it cites.
Maatphor: Automated Variant Analysis for Prompt Injection Attacks, December 2023
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
OpenAI Dev Day · 2023
Cited alongside, same era.
https://openai.com/blog/chatgpt-plugins , 2023
OpenAI Plugins · 2023
Cited alongside, same era.
https://gptstore.ai/ , 2023
Third-Party GPTs Store · 2023
Cited alongside, same era.
https://webreader.webpilotai.com/legal_info.html , 2023
WebPilot ChatGPT Plugin · 2023
Cited alongside, same era.
Jailbreaking black box large language models in twenty queries
Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J Pappas, and Eric Wong · 2023
Cited alongside, same era.
Evaluation of chatgpt model for vulnerability detection, 2023
Anton Cheshkov, Pavel Zadorozhny, and Rodion Levichev · 2023
Cited alongside, same era.
Ahmed Salem, Andrew Paverd, and Boris Köpf · 2023
Later among the works it cites.
Privacy and data protection in chatgpt and other ai chatbots: Strategies for securing user information
Glorin Sebastian · 2023
Later among the works it cites.
An independent evaluation of chatgpt on mathematical word problems (mwp)
Paulo Shakarian, Abhinav Koyyalamudi, Noel Ngu, and Lakshmivihari Mareedu · 2023
Later among the works it cites.
Survey of vulnerabilities in large language models revealed by adversarial attacks
Erfan Shayegani, Md Abdullah Al Mamun, Yu Fu, Pedram Zaree, Yue Dong, and Nael Abu-Ghazaleh · 2023
Later among the works it cites.
Llama: Open and efficient foundation language models
Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al · 2023
Later among the works it cites.
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game, November 2023
Sam Toyer, Olivia Watkins, Ethan Adrian Mendes, Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, Alan Ritter, and Stuart Russell · 2023
Later among the works it cites.
Decodingtrust: A comprehensive assessment of trustworthiness in gpt models, 2023
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, and Bo Li · 2023
Later among the works it cites.
Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection, June 2023
Chaofan Wang, Samuel Kernan Freire, Mo Zhang, Jing Wei, Jorge Goncalves, Vassilis Kostakos, Zhanna Sarsenbayeva, Christina Schneegass, Alessandro Bozzon, and Evangelos Niforatos · 2023
Later among the works it cites.
Jailbreak and guard aligned language models with only few in-context demonstrations, 2023
Zeming Wei, Yifei Wang, and Yisen Wang · 2023
Later among the works it cites.
Unveiling security, privacy, and ethical concerns of chatgpt
Xiaodong Wu, Ran Duan, and Jianbing Ni · 2023
Later among the works it cites.
Benchmarking and defending against indirect prompt injection attacks on large language models
Jingwei Yi, Yueqi Xie, Bin Zhu, Keegan Hines, Emre Kiciman, Guangzhong Sun, Xing Xie, and Fangzhao Wu · 2023
Later among the works it cites.
Assessing Prompt Injection Risks in 200+ Custom GPTs, November 2023
Jiahao Yu, Yuhang Wu, Dong Shu, Mingyu Jin, and Xinyu Xing · 2023
Later among the works it cites.
Universal and transferable adversarial attacks on aligned language models
Andy Zou, Zifan Wang, J Zico Kolter, and Matt Fredrikson · 2023
Later among the works it cites.
Jatmo: Prompt Injection Defense by Task-Specific Finetuning, January 2024
Julien Piet, Maha Alrashed, Chawin Sitawarin, Sizhe Chen, Zeming Wei, Elizabeth Sun, Basel Alomair, and David Wagner · 2024
Closest in time.
Xuchen Suo · 2024
Closest in time.
Daniel Wankit Yip, Aysan Esmradi, and Chun Fai Chan · 2024
Closest in time.