Jingjing Chen     

Associate Professor
School of Computer Science
Fudan University
  chenjingjing@fudan.edu.cn
Office: No.2 Interdisciplinary Research Building D5021
[Google Scholar]

I am currently an Associate Professor at the School of Computer Science, Fudan University. Prior to joining Fudan, I was a Research Fellow at the School of Computing, National University of Singapore (NUS), working with Prof. Tat-Seng Chua. I received my Ph.D. degree in Computer Science from City University of Hong Kong in July 2018, supervised by Prof. Chong-Wah Ngo. I received several accolades, including “ACM SIGMM Rising Star Award” in 2024, “IEEE ICME Rising Star Runner Up” in 2023, “ACM Shanghai Rising Star Award” in 2020, the “AI 2000 Most Influential Scholar Nomination Award” in 2021, the “Best Paper Award” at ChinaMM 2021, the “Best Student Paper Award” at ACM Multimedia 2016, the “Best Student Paper Award” at Multimedia Modeling 2017. I’m also listed as “Stanford & Elsevier’s Top 2% Scientist” in 2024 etc.

My research primarily focuses on, but is not limited to:

  1. Multimedia Content Analysis: Cross-modal Retrieval, Image/Video Classification, Multi-modal Forgery Detection, Food Recognition, and Nutrition Analysis
  2. Multimedia Model Security: Adversarial Attack and Defense, Transferable Adversarial Attack, Backdoor Attack, Adversarial Training, Adversarial Robustness Evaluation for Large Multi-modal Models, Unsafe Concept Removal for Generative Models

  Open Positions
  • I am recruiting research fellow (holding a doctoral degree) with relevant research experience on Multimedia Contents Analysis and Generative AI. Candidates are expected to have publications in top conferences (NeurIPS, ICLR, ICML, CVPR, ECCV, ICCV, AAAI, ACM-MM, etc.) or high-impact journals (T-PAMI, TIP, TMM, IJCV, etc.). Qualified candidates are welcome to apply.
  • I am looking for 2-3 interns working on Generative AI Security. Please feel free to email me with your CV if you are interested.
  • Currently, there are no openings for PhD students starting in Fall 2025.

What's New
Research Highlights

Multimedia Forgery Detection

We work on constructing high quality datasets for training and evaluating deepfake detection models. We published one of the earliest datasets WildDeepFake [ACM MM’20] for evaluating the performance of deepfake detection models against real-world deepfakes sourced from the internet. Recently, we introduced IDForge [ACM MM’24], the largest multimodal deepfake detection dataset to date, encompassing nine of the most popular manipulation types across visual, audio, and textual modalities. In addition to dataset constrcution, we also work on enhancing deepfake detection accuracy and generalization. This includes employing uncertainty-aware learning [ACM MM’23] and developing multimodal approaches like multimodal identity reference-assisted detection [ACM MM’24].

Adversarial Robustness Evaluation for Multimedia Models

We work on efficient robustness adversarial evaluation approaches for complex multimedia models. We develop transfer-based adversarial attack methods which enhance the transferability through diverse input generation, such as temporal translation [AAAI 2022], random cropping [CVPR 2023], for black-box attack on video models. We also investigate the possibility of cross-modal attack [CVPR 2022] which crafts adversarial perturbations on images models for attacking video models, as well as task-agnostic attack which evaluate the robustness of pre-trained vision-language models (e.g., CLIP) [ICME 2023]. Beyond those restricted adversarial attack, we recently investigated un-restricted attack which directly generate adversarial examples using diffusion models to alter few pixels to perform attack on video models as well as VL models [ACM MM 2024 b, ACM MM 2024 c].

Responsible Generative AI

We recently published two papers on removing unsafe concepts in diffusion models. In ECCV 2024, we introduced Reliable and Efficient Concept Erasure (RECE), a novel approach that enables modification of the model within 3 seconds, without requiring additional fine-tuning. Additionally, we have another work - Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concept. This work has been accepted for AAAI 2025. In addition to unsafe concept removal, we are also focusing on AI-generated content identification and Offensive and Non-compliant Content Attribution, with the goal of fostering responsible generative AI. These works will be available on arXiv soon.

AI + Health (Interdisciplinary Research)

We work on an interesting and useful application that aim to improve human health using AI technologies. We published one of the earliest works on Large Multi-modal Model in food domain, named as FoodLMM [accepted by TMM 2025]. Moreover, we also work on Weight and Health Prediction Based on Food Logs [ACM MM 2024], Food Image and Nutrition Analysis, Diet Suggestion Generation Using Large Multimodal Models (LMMs)) etc.

Publications
Teaching
Academic Services
Team Time
Team Christmas2024
Merry Christmas 2024!

2024-December


We celebrate Christmas at the Anji Resort, enjoying hot springs, gourmet food, karaoke, and skiing. A heartfelt thanks to Yue Yu, Jiayu Wang, Pinye Chen, Xueqiao Wang, Junhao Xu, and Xinghan Li for their hard work in securing the activity funds that made this unforgettable experience possible!

Team 2024 Freshman

Welcome new team members!

2024-9-1


This year, we welcome new team members: Jiarui Yang, Chao Gong, Yian Li, Xinghan Li, Xueqiao Wang, Jianrong Yan, Tianxiao Xu, Shijie Zhou, and Xiaoyu Chen.

Farewell to the Class of 2024

Farewell to the Class of 2024!

2024-June


This year, we have two doctoral graduates, Zhipeng Wei and Tianwen Qian, along with seven master's graduates: Zixuan Su, Yuehao Yin, Huiyan Qi, Yanqi Wu, Yue Yu, Wenzhuo Xu, and Yiqiang Lv. We wish them all the best in pursuing their dreams~

2023 Christmas

Merry Christmas!

2023-December


We celebrate Christmas at a party venue, enjoying the entertainment facilities, cooking together, and all the happy times.

Group Members
PhD Students:
  • Jiarui Yang (September 2024 – present) homepage
  • Yue Yu (September 2024 – present)
  • Guoshan Liu (September 2024 – present)
  • Xue Song (September 2021 – present)
  • Yang Jiao (September 2021 – present) homepage
  • Pengkun Jiao (September 2021 – present) homepage
  • Kai Chen (September 2020 – present)
Master Students:
  • Chao Gong, (September 2024 – present)
  • Yian Li, (September 2024 – present)
  • Xinghan Li, (September 2024 – present)
  • Xueqiao Wang, (September 2024 – present)
  • Jianrong Yan, (September 2024 – present)
  • Tianxiao Xu, (September 2024 – present)
  • Shijie Zhou, (September 2024 – present)
  • Xiaoyu Chen, (September 2024 – present)
  • Ziyi Gao, (September 2023 – present)
  • Junhao Xu, (September 2023 – present)
  • Pinye Chen, (September 2023 – present)
  • Feng Han, (September 2023 – present)
  • Jiayu Wang, (September 2023 – present)
  • Xinlan Wu, (September 2023 – present)
  • Yinxuan Gui, (September 2022 – present)
  • Haoxiang Chen, (September 2022 – present)
  • Jiacheng Zhang, (September 2022 – present)
  • Wentao Tian, (September 2022 – present)
Former Members
  • Zhipeng Wei (Ph.D. student): September 2021 - June 2024, now at UC Berkeley as Postdoc researcher
    - Thesis title: Adversarial Robustness Evaluation for Deep Visual Models
  • Tianwen Qian (Ph.D. student): September 2019 - June 2024, now at ECNU as Pre-tenured Associate Professor
    - Thesis title: Multi-modal Visual Question Answering
  • Linhai Zhuo (Ph.D. student): September 2019 - June 2023, now at Fuzhou University as Lecturer
    - Thesis title: Few-shot Image Recognition with Knowledge Transfer
  • Zixuan Su (Master Student): September 2021 - January 2024, Now at Tencent
  • Yuehao Yin (Master Student): September 2021 - January 2024
  • Huiyan Qi (Master Student): September 2021 - January 2024, now at SMU as Research Associate
  • Yanqi Wu (Master Student): September 2021 - June 2024, Now at Papal.
  • Yue Yu (Master Student): September 2021 - June 2024, now pursuing PhD degree at Fudan
  • WenZhuo Xu (Master Student): September 2021 - June 2024, now at 360
  • Yiqiang Lv (Master Student): September 2021 - June 2024, now at Pinduoduo
  • Jianggang Zhu (Master Student): September 2020 - January 2023
  • Fan Luo(Master Student): September 2020 - January 2023, now at Century Frontier Asset Management
  • Xueqing Zhou (Master Student): September 2019 - June 2024, now at Antgroup
  • Jixiang Gao (Master Student): September 2019 - January 2022, now at Antgroup
  • Jianlong Wu(Master Student): September 2019 - January 2022, now running a startup company
  • Jinmian Cai(Master Student): September 2019 - January 2022,now at Tencent
  • Tao Sha (Master Student): September 2019 - January 2022, now at Ctrip
Miscellaneous

When I have spare time, I enjoy cooking.

Webpage template borrowed from Prof. Wei Xu.