Zheling Meng

Ph.D. Candidate @ CASIA, NLPR

Welcome to my page!

About Me

I am pursing my Ph.D. degree at Institute of Automation, Chinese Academy of Sciences (CASIA). Before that, I received my double B.S. degree in Xi'an Jiaotong University (XJTU) in 2020.

My research interests mainly focus on these aspects:
  • AI Safety: Knowledge editing/erasure, truthworthy generation.
  • AI for security: Privacy protection, deepfake detection.
  • AI for science: Medicine, biology.

[JOIN US] If you are interested in our work and would like to join us, please feel free to contact me.

[NEWS] Our paper has been awarded the PRCV Best Paper Award and the CCF Outstanding Paper Award.

Education

2023.09 - Now
Ph.D. Candidate in Computer Sciences @ CASIA

New Laboratory of Pattern Recognition (NLPR)

State Key Laboratory of Multimodal Artificial Intelligence Systems

Supervisor: Prof. Tieniu Tan (Co-Supervisor: Prof. Jing Dong)

2020.09 - 2023.06
M.S. in Pattern Recognition and Intelligent Systems @ CASIA

CAS Key Laboratory of Moleculer Imaging

Supervisor: Prof. Kun Wang

2016.09 - 2020.06
B.S. in Information Engineering & B.S. in Finance @ XJTU

School of Information and Communication Engineering

Internship

2025.07 - 2025.08
Big Security @ Ant Group
2024.12 - 2025.05
Security and Risk Control @ Bytedance Group
2021.12 - 2022.10
Intelligent City and Business @ Sensetime

Awards

  • 2024.06 Three Good Student, UCAS
  • 2024.06 Excellent Student Leader, UCAS
  • 2023.06 Three Good Student Model (~Top 1%), UCAS
  • 2022.10 National Scholarship (~Top 1%), Ministry of Education of PRC
  • 2020.06 Wenzhi Model, XJTU
  • 2020.04 Outstanding Graduate, XJTU

Professional Services

Teaching Assistant

Course Name: Artificial Intelligence Security, Attacks and Defenses (GitHub)

Course Offering: School of Artificial Intelligence @ UCAS

Reviewer

IEEE T-IFS

ICLR, CVPR, ECCV, AAAI, PRCV

Society Member

IEEE, CSIG, CAAI

Selected Papers

  1. [PRCV, Best Paper] Concept Corrector: Erase concepts on the fly for text-to-image diffusion models
    2025, PDF, Code
  2. [arXiv] Dark Miner: Defend against undesired generation for text-to-image diffusion models
    2024, PDF, Code
  3. [T-MM] Latent watermark: Inject and detect watermarks in latent diffusion space
    2025, PDF, Code
  4. [CVIU] Artifact feature purification for cross-domain detection of AI-generated images
    2024, PDF, Code
  5. [T-MI] MSMFN: an ultrasound based multi-step modality fusion network for identifying the histologic subtypes of metastatic cervical lymphadenopathy
    2022, PDF, Code
  6. [ISBI] CEUSegNet: A cross-modality lesion segmentation network for contrast-enhanced ultrasound
    2022, PDF, Code
  7. [BMC Medicine] Cervical lymph node metastasis prediction from papillary thyroid carcinoma US videos: a prospective multicenter study
    2024, PDF, Code
  8. [BMC Medicine] Deep learning radiomics of dual-modality ultrasound images for hierarchical diagnosis of unexplained cervical lymphadenopathy
    2022, PDF, Code