Selected Publications

For a complete list of publications, please see my Google Scholar profile .

2026

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models

Anshuman Suri*, Harsh Chaudhari*, Yuefeng Peng*, Ali Naseh*, and Alina Oprea, Amir Houmansadr

* Equal contribution

IEEE S&P (Oakland) — 2026

arXiv Code

2025

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security

Ali Naseh, Anshuman Suri, Yuefeng Peng, Harsh Chaudhari, Alina Oprea, Amir Houmansadr

Lock-LLM Workshop, NeurIPS — 2025

arXiv

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis

Anushka Yadav, Isha Nalawade, Srujana Pillarichety, Yashwanth Babu, Reshmi Ghosh, Samyadeep Basu, Wenlong Zhao, Ali Naseh, Sriram Balasubramanian, Soundararajan Srinivasan

Foundations of Reasoning Language Models workshop, NeurIPS — 2025

arXiv

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

Ali Naseh*, Yuefeng Peng*, Anshuman Suri*, Harsh Chaudhari, Alina Oprea, Amir Houmansadr

* Equal contribution

ACM CCS — 2025

arXiv Paper Code

Throttling Web Agents Using Reasoning Gates

Abhinav Kumar, Jaechul Roh, Ali Naseh, Amir Houmansadr, Eugene Bagdasarian

Preprint — 2025

arXiv Code

Backdooring Bias (B²) into Stable Diffusion Models

Ali Naseh, Jaechul Roh, Eugene Bagdasarian, Amir Houmansadr

USENIX Security — 2025

arXiv Paper Code

R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model

Ali Naseh, Harsh Chaudhari, Jaechul Roh, Mingshi Wu, Alina Oprea, Amir Houmansadr

Preprint — 2025

arXiv

Diffence: Fencing Membership Privacy With Diffusion Models

Yufeng Peng, Ali Naseh, Amir Houmansadr

NDSS — 2025

arXiv Paper Code

OVERTHINK: Slowdown Attacks on Reasoning LLMs

Abhinav Kumar, Jaechul Roh, Ali Naseh, Marzena Karpinska, Mohit Iyyer, Amir Houmansadr, Eugene Bagdasarian

Preprint — 2025

arXiv Code

Synthetic data can mislead evaluations: Membership inference as machine text detection

Ali Naseh, Niloofar Mireshghallah

Preprint — 2025

arXiv

2024

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images

Ali Naseh, Katherine Thai, Mohit Iyyer, Amir Houmansadr

COLM — 2024 🔦 Oral Spotlight

arXiv Paper Talk

2023

Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication

Ali Naseh, Jaechul Roh, Amir Houmansadr

Privacy-Preserving Artificial Intelligence (PPAI) Workshop, AAAI — 2023

arXiv

Stealing the Decoding Algorithms of Language Models

Ali Naseh, Kalpesh Krishna, Mohit Iyyer, Amir Houmansadr

ACM CCS — 2023 🏆 Distinguished Paper Award

arXiv Paper