Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks

S. E. Robertson and S. Walker, “Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval,” in Annual International ACM SIGIR Conference on Research and Development in Information Retrieval , 1994. [Online]. Available: https://api.semanticscholar.org/CorpusID:2218552

1994

Earlier work this paper cites.

C. Song, A. M. Rush, and V. Shmatikov, “Adversarial semantic collisions,” in Conference on Empirical Methods in Natural Language Processing , 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:224461948

2020

Earlier work this paper cites.

N. Raval and M. Verma, “One word at a time: adversarial attacks on retrieval models,” ArXiv , vol. abs/2008.02197, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:220968803

Original

2020

Earlier work this paper cites.

W. Wang, F. Wei, L. Dong, H. Bao, N. Yang, and M. Zhou, “Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers,” ArXiv , vol. abs/2002.10957, 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:211296536

Original

2020

Earlier work this paper cites.

J. Liu, Y. Kang, D. Tang, K. Song, C. Sun, X. Wang, W. Lu, and X. Liu, “Order-disorder: Imitation adversarial attacks for black-box neural ranking models,” in Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security , 2022

2022

Earlier work this paper cites.

A. T. Mallen, A. Asai, V. Zhong, R. Das, H. Hajishirzi, and D. Khashabi, “When not to trust language models: Investigating effectiveness of parametric and non-parametric memories,” in Annual Meeting of the Association for Computational Linguistics , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:254877603

2022

Earlier work this paper cites.

Y. Wang, L. Lyu, and A. Anand, “Bert rankers are brittle: A study using adversarial document perturbations,” Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:249953753

2022

Earlier work this paper cites.

J. Song, J. Zhang, J. Zhu, M. Tang, and Y. Yang, “Trattack”:” text rewriting attack against text retrieval,” in Workshop on Representation Learning for NLP , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:248780479

2022

Earlier work this paper cites.

N. Kandpal, H. Deng, A. Roberts, E. Wallace, and C. Raffel, “Large language models struggle to learn long-tail knowledge,” in International Conference on Machine Learning , 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:253522998

2022

Earlier work this paper cites.

Y. Bai, A. Jones, K. Ndousse, A. Askell, A. Chen, N. DasSarma, D. Drain, S. Fort, D. Ganguli, T. Henighan et al. , “Training a helpful and harmless assistant with reinforcement learning from human feedback,” arXiv preprint arXiv:2204.05862 , 2022

Original

2022

Earlier work this paper cites.

K. Greshake, S. Abdelnabi, S. Mishra, C. Endres, T. Holz, and M. Fritz, “Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,” in Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security , 2023, pp. 79–90

2023

Earlier work this paper cites.

X. Chen, B. He, Z. Ye, L. Sun, and Y. Sun, “Towards imperceptible document manipulations against neural ranking models,” in Findings of the Association for Computational Linguistics (ACL) , 2023

2023

Earlier work this paper cites.

C. Wu, R. Zhang, J. Guo, M. De Rijke, Y. Fan, and X. Cheng, “Prada: Practical black-box adversarial attacks against neural ranking models,” vol. 41, no. 4, 2023

2023

Earlier work this paper cites.

X. Chen, B. He, Z. Ye, L. Sun, and Y. Sun, “Towards imperceptible document manipulations against neural ranking models,” in Annual Meeting of the Association for Computational Linguistics , 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:258461344

2023

Earlier work this paper cites.

Z. Lin, Z. Li, X. Liao, X. Wang, and X. Liu, “Mawseo: Adversarial wiki search poisoning for illicit online promotion,” ArXiv , vol. abs/2304.11300, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:258298256

Original

2023

Cited alongside, same era.

Z. Zhong, Z. Huang, A. Wettig, and D. Chen, “Poisoning retrieval corpora by injecting adversarial passages,” ArXiv , vol. abs/2310.19156, 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:264828956

Original

2023

Cited alongside, same era.

Y. Liu, R. Zhang, J. Guo, M. de Rijke, W. Chen, Y. Fan, and X. Cheng, “Topic-oriented adversarial attacks against black-box neural ranking models,” Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval , 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:258418289

2023

Cited alongside, same era.

——, “Black-box adversarial attacks against dense retrieval models: A multi-view contrastive learning method,” Proceedings of the 32nd ACM International Conference on Information and Knowledge Management , 2023. [Online]. Available: https://api.semanticscholar.org/CorpusID:261049237

OWASP, “Owasp top 10 for llms and generative ai apps,” https://genai.owasp.org/llm-top-10/ , [Accessed 19-05-2024]

2024

Closest in time.

X. Shen, Y. Qu, M. Backes, and Y. Zhang, “Prompt stealing attacks against text-to-image generation models,” 2024

2024

Closest in time.

J. Evertz, M. Chlosta, L. Schönherr, and T. Eisenhofer, “Whispers in the machine: Confidentiality in llm-integrated systems,” in ArXiv , 2024

2024

Closest in time.

“Introduction — LangChain — python.langchain.com,” https://python.langchain.com/docs/get_started/introduction/ , [Accessed 24-04-2024]

2024

Closest in time.

“LlamaIndex - LlamaIndex — docs.llamaindex.ai,” https://docs.llamaindex.ai/en/stable/ , [Accessed 24-04-2024]

2024

Closest in time.