Hello,I am Qian Jiang,a sophomore computer science undergraduate student at Northeastern University. (These pages are available on the https://pbrqianjiang.github.io/)

I am very fortunate to be advised by Xiuying Chen of NLP Lab from mbzuai University.I am honored to be advised by Miao Fang of Language & Intelligence Systems Lab from Northeastern University

In addition, I am lucky to serve as the student leader of NEUQ LIS Lab in 2025-2026, responsible for the operation and recruitment of new members of the lab,a place staffed by undergraduates.

I am currently actively seeking for Online or offline research internships or future PhD opportunities. If you have any relevant opportunities or suggestions, please feel free to contact me.I am very excited to discuss potential collaborations.

Research Interesting

-Trustworthy AI：My research interests are security and interpretability in the field of trustworthy AI (intersecting with various modalities) , multimodality,other field in deep learning.

-Diffusion & RL(future):I am currently researching safe alignment based on the properties of diffusion, and am curious about the impact of using RLVR and SFT

Educations

2023.09 - 2027.06 : B.E., Northeastern University(NEU) GPA:4.33/5,rank:1/196

2024.11 - now : intern, Mohamed bin Zayed University of Artificial Intelligence(mbzuai)

Publications

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models

Zirui Song*, Qian Jiang*, Mingxuan Cui*, Mingzhe Li, Lang Gao, Zeyu Zhang, Zixiang Xu, Yanbo Wang, Chenxi Wang, Guangxian Ouyang, Zhenhao Chen, Xiuying Chen (*: first co-authors)

“AJailBench: LAM safety jailbreak benchmark. Evaluates vulnerability using adversarial audio. Reveals LAMs lack robustness.”

Proficiencies

GPA:4.33/5.00 (rank:1/196 in Computer Science and Technology major up to 2025.5)

You can find my CV here: qian_jiang’s Curriculum Vitae.