Scholar
Fahad Shamshad
Google Scholar ID: d7QL4wkAAAAJ
MBZUAI
AI Safety
Generative AI
Multimodal AI
Deepfakes
Medical Imaging
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,965
H-index
13
i10-index
18
Publications
20
Co-authors
30
list available
Publications
12 items
Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering
2026
Cited
0
Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models
2026
Cited
0
SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training
2026
Cited
0
Towards Calibrating Prompt Tuning of Vision-Language Models
2026
Cited
0
RAVEN: Erasing Invisible Watermarks via Novel View Synthesis
2026
Cited
0
SPQR: A Standardized Benchmark for Modern Safety Alignment Methods in Text-to-Image Diffusion Models
2025
Cited
0
Calibration-Aware Prompt Learning for Medical Vision-Language Models
2025
Cited
0
First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge
2025
Cited
0
Load more
Co-authors
16 total
Salman Khan
MBZUAI, Australian National University
Fahad Shahbaz Khan
MBZUAI, Linköping University Sweden
Muhammad Haris Khan
Faculty at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) - UAE
Karthik Nandakumar
Michigan State University, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)
Huazhu Fu
Principal Scientist, IHPC, A*STAR
Syed Waqas Zamir
Sr. Research Scientist @ Microsoft AI for Good Lab
Muzammal Naseer
Asst. Professor, Khalifa University
Junaid Qadir
Professor of Computer Engineering, Qatar University
