Learning to Watermark in the Latent Space of Generative Models Sylvestre-Alvise Rebuffi, Tuan Tran, Valeriu Lacatusu, Pierre Fernandez, Tomáš Souček, Nikola Jovanović, Tom Sander, Hady Elsahar, Alexandre Mourachko. Learning to Watermark in the Latent Space of Generative Models. Preprint, 2026. Jan, 2026. HTML arXiv How Good is Post-Hoc Watermarking With Language Model Rephrasing? Pierre Fernandez, Tom Sander, Hady Elsahar, Haonan Chang, Tomáš Souček, Vlad Lacatusu. How Good is Post-Hoc Watermarking With Language Model Rephrasing?. Preprint, 2026. Jan, 2026. HTML arXiv Pixel Seal: Adversarial-Only Training for Invisible Image and Video Watermarking Tomáš Souček, Pierre Fernandez, Hady Elsahar, Sylvestre-Alvise Rebuffi, Valeriu Lacatusu, Tuan Tran, Tom Sander, Alexandre Mourachko. Pixel Seal: Adversarial-Only Training for Invisible Image and Video Watermarking. Preprint, 2025. Dec, 2025. HTML arXiv Rethinking the Role of Verbatim Memorization in LLM Privacy Tom Sander, Bargav Jayaraman, Mark Ibrahim, Chuan Guo, Kamalika Chaudhuri. Rethinking the Role of Verbatim Memorization in LLM Privacy. NeurIPS, 2025. Jun, 2025. HTML PDF Detecting Benchmark Contamination through Watermarking Tom Sander, Pierre Fernandez, Saeed Mahloujifar, Alain Durmus, Chuan Guo. Detecting Benchmark Contamination through Watermarking. ICLR Workshop, 2025. Feb, 2025. HTML arXiv Watermark Anything with Localized Messages Tom Sander, Pierre Fernandez, Alain Durmus, Teddy Furon, Matthijs Douze. Watermark Anything with Localized Messages. International Conference on Learning Representations (ICLR). Jan, 2025. HTML arXiv PDF Bib Log-normal Mutations and their Use in Detecting Surreptitious Fake Images Ismail Labiad, Thomas Bäck, Pierre Fernandez, Laurent Najman, Tom Sander, Furong Ye, Mariia Zameshina, Olivier Teytaud. Log-normal Mutations and their Use in Detecting Surreptitious Fake Images. Preprint, 2024. Sep, 2024. HTML arXiv Watermarking Makes Language Models Radioactive Tom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon. Watermarking Makes Language Models Radioactive. Neurips 2024 (Spotlight). Apr, 2024. HTML arXiv PDF Bib Differentially Private Representation Learning via Image Captioning Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo. Differentially Private Representation Learning via Image Captioning. International Conference of Machine Learning (ICML). Mar, 2024. HTML arXiv PDF Bib Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training Tom Sander, Maxime Sylvestre, Alain Durmus. Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training. International Conference on Artificial Intelligence and Statistics (AISTATS). Feb, 2024. HTML arXiv PDF Bib TAN Without a Burn: Scaling Laws of DP-SGD Tom Sander, Pierre Stock, Alexandre Sablayrolles. TAN Without a Burn: Scaling Laws of DP-SGD. International Conference of Machine Learning (ICML). Jul, 2023. HTML arXiv Code PDF Bib
