Extracting Prompts by Inverting LLM Outputs

23 May 2024

Papers citing "Extracting Prompts by Inverting LLM Outputs"

21 / 21 papers shown

Title
When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins Yigitcan Kaya Anton Landerer Stijn Pletinckx Michelle Zimmermann Christopher Kruegel Giovanni Vigna SILM 452 0 0 08 Nov 2025
Diffusion LLMs are Natural Adversaries for any LLM David Lüdke Tom Wollschlager Paul Ungermann Stephan Günnemann Leo Schwinn DiffM 156 0 0 31 Oct 2025
Language Models are Injective and Hence Invertible Giorgos Nikolaou Tommaso Mencattini Donato Crisostomi Andrea Santilli Yannis Panagakis Emanuele Rodolà 160 3 0 17 Oct 2025
A global log for medical AI Ayush Noori Adam Rodman Alan Karthikesalingam Bilal A. Mateen Christopher A. Longhurst ... Noa Dagan David Clifton Ran D. Balicer I. Kohane Marinka Zitnik 144 0 0 05 Oct 2025
Depth Gives a False Sense of Privacy: LLM Internal States Inversion Tian Dong Yan Meng Shaofeng Li Guoxing Chen Zhen Liu Haojin Zhu AAML 141 2 0 22 Jul 2025
Privacy Risks of LLM-Empowered Recommender Systems: An Inversion Attack PerspectiveACM Conference on Recommender Systems (RecSys), 2025 Yubo Wang Min Tang Nuo Shen Shujie Cui Weiqing Wang 60 1 0 20 Jul 2025
DP-Fusion: Token-Level Differentially Private Inference for Large Language Models Rushil Thareja Preslav Nakov Praneeth Vepakomma Nils Lukas 150 0 0 06 Jul 2025
Better Language Model Inversion by Compactly Representing Next-Token Distributions Murtaza Nazir Matthew Finlayson John X. Morris Xiang Ren Swabha Swayamdipta 168 4 0 20 Jun 2025
Discrete Diffusion in Large Language and Multimodal Models: A Survey Runpeng Yu Qi Li Xinchao Wang DiffM AI4CE 447 21 0 16 Jun 2025
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality Ruhan Wang Zhiyong Wang Chengkai Huang Rui Wang Tong Yu Lina Yao John C. S. Lui Dongruo Zhou 164 2 0 09 Jun 2025
Harnessing the Universal Geometry of Embeddings Rishi Jha Collin Zhang Vitaly Shmatikov John X. Morris 389 25 0 18 May 2025
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts Hanhua Hong Chenghao Xiao Yang Wang Y. Liu Wenge Rong Chenghua Lin 241 3 0 29 Apr 2025
Universal Zero-shot Embedding Inversion Collin Zhang John X. Morris Vitaly Shmatikov 608 3 0 31 Mar 2025
Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices Liang Luo Bowei Tian Sihan Chen Yu Li Zheyu Shen Myungjin Lee Ang Li 182 2 0 19 Mar 2025
GraphEval: A Lightweight Graph-Based LLM Framework for Idea EvaluationInternational Conference on Learning Representations (ICLR), 2025 Tao Feng Yihang Sun Jiaxuan You 359 14 0 16 Mar 2025
Prompt Inversion Attack against Collaborative Inference of Large Language ModelsIEEE Symposium on Security and Privacy (S&P), 2025 Wenjie Qu Yuguang Zhou Yongji Wu Tingsong Xiao Binhang Yuan Yongbin Li Jiaheng Zhang 332 8 0 12 Mar 2025
Prompt Inference Attack on Distributed Large Language Model Inference Frameworks Xinjian Luo Ting Yu X. Xiao AAML SILM 370 4 0 12 Mar 2025
IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector Zheng Chen Yushi Feng Changyang He Yue Deng Hongxi Pu Yue Liu Haoxuan Li Bo Li DeLMO 217 1 0 21 Feb 2025
Label Anything: An Interpretable, High-Fidelity and Prompt-Free AnnotatorIEEE International Conference on Robotics and Automation (ICRA), 2025 Wei-Bin Kou Guangxu Zhu Rongguang Ye Shuai Wang Ming Tang Yik-Chung Wu 183 3 0 05 Feb 2025
PromptKeeper: Safeguarding System Prompts for LLMs Zhifeng Jiang Zhihua Jin Guoliang He AAML SILM 401 2 0 18 Dec 2024
Privacy in Large Language Models: Attacks, Defenses and Future Directions Haoran Li Yulin Chen Jinglong Luo Weijing Chen Xiaojin Zhang Qi Hu Chunkit Chan Yangqiu Song PILM 379 62 0 16 Oct 2023