Mehrdad Saberi

15 papers A* 2Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text.
CoRR
Yize Cheng, Vinu Sankar Sadasivan, Mehrdad Saberi, Shoumik Saha, Soheil Feizi
2025 J jnl
IConMark: Robust Interpretable Concept-Based Watermark For AI Images.
CoRR
Vinu Sankar Sadasivan, Mehrdad Saberi, Soheil Feizi
2025 — conf
Mitigating Compositional Failures in Text-to-Image Models with Causal Text Embedding Refinement.
PerCom Workshops
Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Adrienne Raglin, Anjon Basak, Soheil Feizi
2025 J jnl
Model State Arithmetic for Machine Unlearning.
CoRR
Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander, Soheil Feizi
2024 J jnl
DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking.
CoRR
Mehrdad Saberi, Vinu Sankar Sadasivan, Arman Zarei, Hessam Mahdavifar, Soheil Feizi
2024 A* conf
PRIME: Prioritizing Interpretability in Failure Mode Extraction.
ICLR
Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi
2024 J jnl
Robust Routing Made Easy: Reinforcing Networks Against Non-Benign Faults.
IEEE/ACM Trans. Netw.
Christoph Lenzen, Moti Medina, Mehrdad Saberi, Stefan Schmid
2024 A* conf
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks.
ICLR
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi
2024 J jnl
Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models.
CoRR
Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Soheil Feizi
2023 J jnl
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods.
CoRR
Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj, Atoosa Malemir Chegini, Daniela Massiceti, Maziar Sanjabi, Shell Xu Hu, Soheil Feizi
2023 J jnl
PRIME: Prioritizing Interpretability in Failure Mode Extraction.
CoRR
Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi
2023 J jnl
Robust Routing Made Easy: Reinforcing Networks Against Non-Benign Faults.
CoRR
Christoph Lenzen, Moti Medina, Mehrdad Saberi, Stefan Schmid
2023 J jnl
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks.
CoRR
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi
2023 J jnl
ZeroGrad: Costless conscious remedies for catastrophic overfitting in the FGSM adversarial training.
Intell. Syst. Appl.
Zeinab Golgooni, Mehrdad Saberi, Masih Eskandar, Mohammad Hossein Rohban
2021 J jnl
ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training.
CoRR
Zeinab Golgooni, Mehrdad Saberi, Masih Eskandar, Mohammad Hossein Rohban