Scholar
Ali Naseh
Google Scholar ID: 1K2KvWwAAAAJ
University of Massachusetts Amherst
Citations & Impact
Citations
108
H-index
5
i10-index
3
Publications
13
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Paper “Exploiting Leaderboards for Large-Scale Distribution of Malicious Models” accepted at IEEE S&P 2026
- Paper “Backdooring Bias (B²) into Stable Diffusion Models” accepted at USENIX 2025
- Paper “Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation” accepted at CCS 2025
- Paper “Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images” accepted at COLM 2024, selected for oral spotlight presentation (top 2%)
- Paper “Diffence: Fencing Membership Privacy With Diffusion Models” accepted at NDSS 2025
- Paper “Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication” accepted at PPAI 2024
- Paper “Stealing the decoding algorithms of language models” accepted at CCS 2023 and awarded Distinguished Paper Award
- Gave a talk titled “Stealing the decoding algorithms of language models” at New England Security Day 2024
- Received Distinction Award for Portfolio Excellence from Manning College, UMass Amherst in May 2024
