Changjiang Li

Stony Brook, NY, 11790

I am currently a third-year Ph.D. student at Stony Brook University, supervised by Dr. Ting Wang. Prior to transferring to Stony Brook in 2023, I was a Ph.D. candidate at Penn State. I earned my Bachelor’s degree from Tianjin University and my Master’s degree from Zhejiang University (supervised by Dr. Shouling Ji). My research interests encompass adversarial machine learning, large language models, and deepfake detection.

news

Mar 12, 2024	One paper got accepted by AsiaCCS!
Mar 12, 2024	One paper got accepted by ICME!
Feb 3, 2024	One paper got accepted by ICSE Industry Challenge Track!
Jan 22, 2024	One paper got accepted by TDSC!
Dec 22, 2023	I was invited to serve as a reviewer for ICML ‘24!

selected publications

2024

Difficulty

On the Difficulty of Defending Contrastive Learning against Backdoor Attacks

Changjiang Li, Ren Pang, Zhaohan Cao, and 3 more authors

In The 33nd USENIX Security Symposium (Security ’24), 2024

Bib

@inproceedings{li2024on,
  title = {On the Difficulty of Defending Contrastive Learning against Backdoor Attacks},
  author = {Li, Changjiang and Pang, Ren and Cao, Bochuan Xi, Zhaohan and Chen, Jinghui and Ji, Shouling and Wang, Ting},
  booktitle = {The 33nd USENIX Security Symposium (Security '24)},
  year = {2024},
  dimensions = {true}
}

2023

CTRL

An Embarrassingly Simple Backdoor Attack against Self-supervised Learning

Changjiang Li, Ren Pang, Zhaohan Xi, and 4 more authors

In The 2023 International Conference on Computer Vision (ICCV ’23), 2023

Bib

@inproceedings{Li2023simple,
  title = {An Embarrassingly Simple Backdoor Attack against Self-supervised Learning},
  author = {Li, Changjiang and Pang, Ren and Xi, Zhaohan and Du, Tianyu and Ji, Shouling and Yao, Yuan and Wang, Ting},
  booktitle = {The 2023 International Conference on Computer Vision (ICCV '23)},
  year = {2023},
  dimensions = {true},
}

2022

LiveBugger

Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era

Changjiang Li, Li Wang, Shouling Ji, and 4 more authors

In The 31st USENIX Security Symposium (Security ’22), 2022

PDF