Bileve: Securing Text Provenance in Large Language Models Against
Spoofing with Bi-level Signature

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature

4 June 2024

Shaolei Ren

Papers citing "Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature"

6 / 6 papers shown

Title
Unified Attacks to Large Language Model Watermarks: Spoofing and Scrubbing in Unauthorized Knowledge Distillation Xin Yi Shunfan Zhengc Linlin Wanga Xiaoling Wang Liang He Liang He AAML 48 0 0 24 Apr 2025
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search Xuan Chen Yuzhou Nie Wenbo Guo Xiangyu Zhang 98 9 0 28 Jan 2025
Ideal Pseudorandom Codes Omar Alrabiah Prabhanjan Ananth Miranda Christ Yevgeniy Dodis Sam Gunn 30 0 0 08 Nov 2024
Discovering Clues of Spoofed LM Watermarks Thibaud Gloaguen Nikola Jovanović Robin Staab Martin Vechev 30 2 0 03 Oct 2024
Watermark Smoothing Attacks against Language Models Hongyan Chang Hamed Hassani Reza Shokri WaLM 38 2 0 19 Jul 2024
Publicly-Detectable Watermarking for Language Models Jaiden Fairoze Sanjam Garg Somesh Jha Saeed Mahloujifar Mohammad Mahmoody Mingyuan Wang WaLM 139 45 0 27 Oct 2023