Yuefeng Peng

About Me

Hi, I’m Yuefeng Peng, a PhD student in Computer Science at UMass Amherst, advised by Professor Amir Houmansadr. My research centers on trustworthy AI, with a current focus on the safety and privacy of generative models and large language models (LLMs).

News

05/2025: Started internship at Amazon as an Applied Scientist Intern.
02/2025: Attended NDSS 2025 to present our paper Diffence.
12/2024: Attended NeurIPS 2024 to present our paper OSLO.
12/2024: Received the Distinction Award for my PhD portfolio and advanced to candidacy.

Selected Publications

arXiv

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors

Yuefeng Peng*, Junda Wang*, Hong Yu, Amir Houmansadr (*Equal contribution)

arXiv preprint, Nov 2024.

PDF BibTex

Oakland

Exploiting Leaderboards for Large-Scale Distribution of Malicious Models

Anshuman Suri*, Harsh Chaudhari*, Yuefeng Peng*, and Ali Naseh*, Amir Houmansadr, Alina Oprea (*Equal contribution)

IEEE Symposium on Security and Privacy (IEEE S&P), 2026.

PDF BibTex

ACM CCS

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 Conference on Computer and Communications Security (ACM CCS), 2025.

PDF BibTex

NDSS

Diffence: Fencing Membership Privacy With Diffusion Models

Yuefeng Peng, Ali Naseh, Amir Houmansadr

Network and Distributed System Security Symposium (NDSS), 2025.

PDF BibTex

NeurIPS

OSLO: One-Shot Label-Only Membership Inference Attacks

Yuefeng Peng, Jaechul Roh, Subhransu Maji, Amir Houmansadr

Advances in Neural Information Processing Systems (NeurIPS), 2024.

PDF BibTex

About Me

News

Selected Publications

Services

Conference Reviewers

Journal Reviewers