ICLR 2025 Workshop WMARK Submissions

WINTER SOLDIER: HYPNOTIZING LANGUAGE MODELS AT PRE-TRAINING WITH INDIRECT DATA POISONING
Wassim Bouaziz, Mathurin VIDEAU, Nicolas Usunier, El-Mahdi El-Mhamdi
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge
Fahad Shamshad, Tameem Bakr, Yahia Salaheldin Shaaban, Noor Hazim Hussein, Karthik Nandakumar, Nils Lukas
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Towards Watermarking of Open-Source LLMs
Thibaud Gloaguen, Nikola Jovanović, Robin Staab, Martin Vechev
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
SpARK: An Embarrassingly Simple Sparse Watermarking in LLMs with Enhanced Text Quality
Duy Cao Hoang, Thanh Quoc Hung Le, Rui Chu, Ping Li, Weijie Zhao, Yingjie Lao, Khoa D Doan
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
ON-DEVICE WATERMARKING: A SOCIO-TECHNICAL IMPERATIVE FOR AUTHENTICITY IN THE AGE OF GENERATIVE AI
Houssam Kherraz
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models
Fay Elhassan, Niccolò Ajroldi, Antonio Orvieto, Jonas Geiping
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Deep Audio Watermarks are Shallow: Limitations of Post-Hoc Watermarking Techniques for Speech
Patrick O'Reilly, Zeyu Jin, Jiaqi Su, Bryan Pardo
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
Saksham Rastogi, Pratyush Maini, Danish Pruthi
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Watermarking and Metadata for GenAI Transparency at Scale - Lessons Learned and Challenges Ahead
Elizabeth Hilbert, Gretchen Greene, Michael Godwin, Sarah Shirazyan
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Visual Fidelity vs. Robustness: Trade-Off Analysis of Image Adversarial Watermark Mitigated by SSIM Loss
Jiwoo Choi, Jinwoo Kim, Sejong Yang, Seon Joo Kim
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
A Taxonomy of Watermarking Methods for AI-Generated Content
Pierre Fernandez, Hady Elsahar, Sylvestre-Alvise Rebuffi, Tomas Soucek, Valeriu Lacatusu, Tuan Tran, Alexandre Mourachko
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
WaterFlow: Learning Fast & Robust Watermarks using Stable Diffusion
Vinay Shukla, Prachee Sharma, Ryan A. Rossi, Sungchul Kim, Tong Yu, Aditya Grover
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
RINTAW: A Robust Invisible Watermark for Tabular Generative Models
Liancheng Fang, Aiwei Liu, Henry Peng Zou, Hengrui Zhang, Philip S. Yu
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
MultiNeRF: Multiple Watermark Embedding for Neural Radiance Fields
Yash Kulthe, Andrew Gilbert, John Collomosse
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Are Watermarks For Diffusion Models Radioactive?
Jan Dubiński, Michel Meintz, Franziska Boenisch, Adam Dziedzic
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Watermark Smoothing Attacks against Language Models
Hongyan Chang, Hamed Hassani, Reza Shokri
- Published: 06 Mar 2025, Last Modified: 18 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Productionizing Audio Watermarking for Short-Form Video
Elias Lumpert
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
A Watermark for Black-Box Language Models
Dara Bahri, John Frederick Wieting
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Watermarks vs. Perturbations for Preventing AI-based Style Editing
Qiuyu Tang, Aparna Bharati
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
IConMark: Robust Interpretable Concept-Based Watermark For AI Images
Vinu Sankar Sadasivan, Mehrdad Saberi, Soheil Feizi
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Scalable Fingerprinting of Large Language Models
Anshul Nasery, Jonathan Hayase, Creston Brooks, Peiyao Sheng, Himanshu Tyagi, Pramod Viswanath, Sewoong Oh
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Optimized Couplings For Watermarking Large Language Models
Carol Xuan Long, Dor Tsur, Claudio Mayrink Verdun, Hsiang Hsu, Haim H. Permuter, Flavio Calmon
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Models
Ved Umrajkar, Aakash Kumar Singh
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
Haiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao, Yuheng Bu
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone
High payload robust watermarking of generative models with multiple triggers and channel coding
Jianwei Fei, Benedetta Tondi, Mauro Barni
- Published: 06 Mar 2025, Last Modified: 16 Apr 2025
- WMARK@ICLR2025
- Readers: Everyone