Mehrdad Saberi

PhD student, Department of Computer Science, University of Maryland, College Park

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

#5102 · Mucong Ding, Bang An, Tahseen Rabbani, Chenghao Deng, Anirudh Satheesh, Souradip Chakraborty, Mehrdad Saberi, Yuxin Wen, Kyle Rui Sang, Aakriti Agrawal, Xuandong Zhao, Mo Zhou, Mary-Anne Hartley, Lei Li, Yu-Xiang Wang, Vishal M. Patel, Soheil Feizi, Tom Goldstein, Furong Huang

A technical report detailing a NeurIPS competition testing the robustness of popular watermarks and practical guidance for future development.

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

#1401 · Yize CHENG, Vinu Sankar Sadasivan, Mehrdad Saberi, Shoumik Saha, Soheil Feizi

We propose adversarial paraphrasing: a training-free, transferable attack that universally humanizes AI-generated text by using an off-the-shelf LLM as a paraphraser, guided by an AI text detector.