Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases

Adversarial examples in modern machine learning: A review

Original

Rey Reza Wiyatno, Anqi Xu, Ousmane Dia, and Archy De Berker. 2019 · 1911

Earlier work this paper cites.

Membership inference attacks from first principles

Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, and Florian Tramer. 2022 · 1914

Earlier work this paper cites.

Rogue scores

Max Grusky. 2023 · 1934

Earlier work this paper cites.

A density-based algorithm for discovering clusters in large spatial databases with noise

Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu. 1996 · 1996

Earlier work this paper cites.

Language models are few-shot learners

Original

Tom B Brown. 2020 · 2005

Earlier work this paper cites.

spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing

Matthew Honnibal and Ines Montani. 2017 · 2017

Earlier work this paper cites.

Membership inference attacks against machine learning models

Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017 · 2017

Earlier work this paper cites.

Retrieval augmented language model pre-training

Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020 · 2020

Earlier work this paper cites.

Membership inference attacks on sequence-to-sequence models: Is my data in your machine translation system?

Sorami Hisamoto, Matt Post, and Kevin Duh. 2020 · 2020

Earlier work this paper cites.

Retrieval-augmented generation for knowledge-intensive nlp tasks

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020 · 2020

Earlier work this paper cites.

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Taylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace, and Sameer Singh. 2020 · 2020

Earlier work this paper cites.

Extracting training data from large language models

Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021 · 2021

Earlier work this paper cites.

A continual learning survey: Defying forgetting in classification tasks

Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Aleš Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. 2021 · 2021

Earlier work this paper cites.

Membership inference attacks against nlp classification models

Virat Shejwalkar, Huseyin A Inan, Amir Houmansadr, and Robert Sim. 2021 · 2021

Earlier work this paper cites.

A survey on in-context learning

Original

Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Tianyu Liu, et al. 2022 · 2022

Earlier work this paper cites.

A survey on text classification: From traditional to deep learning

Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S Yu, and Lifang He. 2022 · 2022

Earlier work this paper cites.

Quantifying privacy risks of masked language models using membership inference attacks

Fatemehsadat Mireshghallah, Kartik Goyal, Archit Uniyal, Taylor Berg-Kirkpatrick, and Reza Shokri. 2022 · 2022

Earlier work this paper cites.

Considerations for differentially private learning with large-scale public pretraining

Original

Florian Tramèr, Gautam Kamath, and Nicholas Carlini. 2022 · 2022

Earlier work this paper cites.

Text embeddings by weakly-supervised contrastive pre-training

Original

Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022 · 2022

Earlier work this paper cites.

Emergent abilities of large language models

Original

Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022 · 2022

Earlier work this paper cites.

A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity

Original

Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, et al. 2023 · 2023

Cited alongside, same era.

Wild patterns reloaded: A survey of machine learning security against training data poisoning

Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Sebastiano Vascon, Werner Zellinger, Bernhard A Moser, Alina Oprea, Battista Biggio, Marcello Pelillo, and Fabio Roli. 2023 · 2023

Cited alongside, same era.

On the privacy risk of in-context learning

Haonan Duan, Adam Dziedzic, Mohammad Yaghini, Nicolas Papernot, and Franziska Boenisch. 2023 · 2023

Cited alongside, same era.

Machine learning security in industry: A quantitative survey

Kathrin Grosse, Lukas Bieringer, Tarek R Besold, Battista Biggio, and Katharina Krombholz. 2023 · 2023

Cited alongside, same era.

The dark side of artificial intelligence in service: The “watching-eye” effect and privacy concerns

Yaou Hu and Hyounae Kelly Min. 2023 · 2023

Retrieval augmented generation (rag) based restaurant chatbot with ai testability

Vani Bhat, Divya Sree, Jinu Cheerla, Nupur Mathew, Gunna LIu, and Jerry Gao. 2024 · 2024

Closest in time.

Unleashing worms and extracting data: Escalating the outcome of attacks against rag-based inference in scale and severity using jailbreaking

Original

Stav Cohen, Ron Bitton, and Ben Nassi. 2024 · 2024

Closest in time.

Personalized home assistant using large language model with context-based chain of thought reasoning

Adam Cutbill, Eric Monsler, and Eric Hayashi. 2024 · 2024

Closest in time.

Tomorrow brings greater knowledge: Large language models join dynamic temporal knowledge graphs

Christian Di Maio, Andrea Zugarini, Francesco Giannini, Marco Maggini, and Stefano Melacci. 2024 · 2024

Closest in time.

A review on the use of large language models as virtual tutors

Silvia García-Méndez, Francisco de Arriba-Pérez, and María del Carmen Somoza-López. 2024 · 2024

Closest in time.