I am a Ph.D. student in the School of Computing at the University of Connecticut (UConn), advised by Prof. Yuan Hong and co-advised by Prof. Meisam Mohammady.

My research focuses on AI security and privacy, with an emphasis on adversarial attacks against large language models and differentially private machine learning. I am particularly interested in understanding and mitigating privacy risks in AI agents, including how everyday interactions can expose sensitive personal information through indirect inference.

Previously, I worked as a Research and Algorithm Engineer at iFlytek, developing speech recognition and assessment systems, as well as speech-based systems for disease detection. I received my M.S. and B.S. in Electronic Engineering from the University of Electronic Science and Technology of China.

I expect to graduate in May 2027, with flexibility in my graduation timeline, and am seeking research internships and full-time opportunities in 2027 in AI security, privacy, and trustworthy machine learning.

🔥 News

• 2026.07: Our USENIX Security’26 paper got three (Available, Functional/Reusable, Results Reproduced) badges for the artifacts Congrats!
• 2026.05: Received the 2026 UConn Predoctoral Award.
• 2026.05:  🎉🎉 Our work on human-perceptible adversarial attacks on LLM-powered content moderation systems (user studies were first incorporated directly into the attack design pipeline) is accepted to USENIX Security’26. Congrats!
• 2026.02: Presented our ongoing research as a poster at ABSURD 2026 (Annual Boston Security Usability Research Day).
• 2025.10: Our CCS’25 paper got three (Available, Functional/Reusable, Results Reproduced) badges for the artifacts Congrats!
• 2025.09:  🎉🎉 Our paper was accepted to IEEE CSF 2026.
• 2025.07:  🎉🎉 Our paper was accepted to ACM CCS 2025 (ACM Conference on Computer and Communications Security).
• 2025.05: Received the 2025 UConn Predoctoral Award.
• 2023.01: Joined the University of Connecticut as a Ph.D. student.

📝 Publications

• USENIX Security’26 What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
  Qin Yang*, Lu Malloy*, Joshua Lee, Xiaohan Chang, Meisam Mohammady, Doowon Kim and Yuan Hong
  In Proceedings of the 35th USENIX Security Symposium (USENIX Security), Baltimore, MD, USA, August 12-14, 2026 (Acceptance Rate: 362/3,028 = 12.0%) | [PDF] | [Code]

• IEEE CSF 2026 Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
  Meisam Mohammady, Qin Yang, Nicholas Stout, Ayesha Samreen, Han Wang, Christopher J. Quinn, and Yuan Hong In Proceedings of the 39th IEEE Computer Security Foundations Symposium (CSF), Lisbon, Portugal, July 26-29, 2026. | [PDF] | [Code]

• ACM CCS 2025 PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
  Qin Yang*, Nicholas Stout*, Meisam Mohammady, Han Wang, Ayesha Samreen, Christopher Quinn, Yan Yan, Ashish Kundu, and Yuan Hong
  In Proceedings of the 32nd ACM Conference on Computer and Communications Security (CCS), Taipei, Taiwan, October 13-17, 2025 (Acceptance Rate: 316/2,278 = 13.9%) | [PDF] | [Code]

*Equal contributions

📖 Educations

• 2023.01 - present, Ph.D. in Computer Science and Engineering, University of Connecticut (UConn), Storrs, CT, USA.
• 2017.09 - 2020.06, M.S. in Electronic Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China.
• 2013.09 - 2017.06, B.S. in Electronic Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, China.

💻 Work Experience

• 2020.07 - 2022.08, Research and Algorithm Engineer, iFlytek Research, iFLYTEK Co., Ltd., Hefei, China.