Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Irene Solaiman, et al. ”Release Strategies and the Social Impacts of Language Models.” arXiv:1908.09203

Original

1908

Earlier work this paper cites.

Nils Reimers and Iryna Gurevych. ”Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.” arXiv preprint arXiv:1908.10084 (2019)

Original

2019

Earlier work this paper cites.

Miles Brundage and Shahar Avin and Jasmine Wang and Haydn Belfield, et al. ”Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims.” arXiv preprint arXiv:2004.07213 (2020)

Original

2020

Earlier work this paper cites.

Tom B. Brown and Benjamin Mann and Nick Ryder, et al. ”Language Models are Few-Shot Learners.” arXiv preprint arXiv:2005.14165 (2020)

Original

2020

Earlier work this paper cites.

Ari Holtzman and Jan Buys, et al. ”The Curious Case of Neural Text Degeneration.” arXiv preprint arXiv:1904.09751 (2020)

Original

2020

Earlier work this paper cites.

Daniel M. Ziegler and Nisan Stiennon, et al. ”Fine-Tuning Language Models from Human Preferences” arXiv preprint arXiv:1909.08593 (2020)

Original

2020

Earlier work this paper cites.

Wolf Thomas and Debut Lysandre, et al. ”Transformers: State-of-the-Art Natural Language Processing.” Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

2020

Earlier work this paper cites.

Inioluwa Deborah Raji and Andrew Smart, et al. ”Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing.” arXiv preprint arXiv:2001.00973 (2020)

Original

2020

Earlier work this paper cites.

Wallace, Eric and Zhao, Tony and Feng, Shi and Singh, Sameer. ”Concealed Data Poisoning Attacks on NLP Models.” Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2021

Earlier work this paper cites.

Bender Emily M. and Gebru Timnit, et al. ”On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?” Association for Computing Machinery (2021)

2021

Earlier work this paper cites.

Nelson Elhage and Tristan Hume, et al. ”Toy Models of Superposition.” arXiv preprint arXiv:2209.10652 (2022)

Original

2022

Earlier work this paper cites.

OWASP Foundation. (2023). ”Top 10 for LLM Applications.” https://owasp.org/www-project-top-10-for-llm-applications

2023

Earlier work this paper cites.

OpenAI. (2023). ”GPT-4 Technical Report.” https://openai.com/research/gpt-4

2023

Cited alongside, same era.

Anthropic. (2023). ”Many-shot Jailbreaking.” https://www.anthropic.com/research/many-shot-jailbreaking

2023

Cited alongside, same era.

Percy Liang and Rishi Bommasani and Tony Lee, et al. ”Holistic Evaluation of Language Models.” arXiv preprint arXiv:2211.09110 (2023)

Original

2023

Cited alongside, same era.

Sébastien Bubeck, et al. ”Sparks of Artificial General Intelligence: Early experiments with GPT-4.” arXiv preprint arXiv:2303.12712 (2023)

Original

2023

Cited alongside, same era.

Kevin Meng and David Bau, et al. ”Locating and Editing Factual Associations in GPT.” arXiv preprint arXiv:2202.05262 (2023)

Original

2023

Cited alongside, same era.

Kaijie Zhu and Jindong Wang, et al. ”PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts.” arXiv preprint arXiv:2306.04528 (2024)

Original

2024

Later among the works it cites.

Nicholas Carlini and Daniel Paleka, et al. ”Stealing Part of a Production Language Model” arXiv preprint arXiv:2403.06634 (2024)

Original

2024

Later among the works it cites.

Xuchen Suo, et al. ”Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications” arXiv preprint arXiv:2401.07612 (2024)

Original

2024

Later among the works it cites.

Yu Peng and Zewen Long, et al. ”Playing Language Game with LLMs Leads to Jailbreaking.” arXiv preprint arXiv:2411.12762 (2024)

Original

2024

Later among the works it cites.