Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data

29 September 2024

Florian Tramèr

Papers citing "Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data"

10 / 10 papers shown

Title
Beyond Public Access in LLM Pre-Training Data Sruly Rosenblat Tim O'Reilly Ilan Strauss MLAU 47 0 0 24 Apr 2025
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Saksham Rastogi Pratyush Maini Danish Pruthi 35 0 0 18 Apr 2025
Instance-Level Data-Use Auditing of Visual ML Models Zonghao Huang Neil Zhenqiang Gong Michael K. Reiter MLAU 55 0 0 28 Mar 2025
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On Ken Ziyu Liu Christopher A. Choquette-Choo Matthew Jagielski Peter Kairouz Sanmi Koyejo Percy Liang Nicolas Papernot 44 0 0 21 Mar 2025
Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge Xinyue Cui Johnny Tian-Zheng Wei Swabha Swayamdipta Robin Jia WaLM 76 0 0 06 Mar 2025
Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models M. Russinovich Ahmed Salem MU CLL 52 0 0 20 Feb 2025
Adversarial ML Problems Are Getting Harder to Solve and to Evaluate Javier Rando Jie Zhang Nicholas Carlini F. Tramèr AAML ELM 52 3 0 04 Feb 2025
Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection Ali Naseh Niloofar Mireshghallah 46 0 0 20 Jan 2025
A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models Bowen Chen Namgi Han Yusuke Miyao 93 0 0 18 Dec 2024
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models Haritz Puerto Martin Gubri Sangdoo Yun Seong Joon Oh MIALM 584 2 2 31 Oct 2024