α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Changjiang Li
Changjiang Li
1
Affiliations
Affiliations
Stony Brook
4
papers
124
total citations
papers (4)
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
NEURIPS 2023
arXiv
46
citations
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
ICCV 2023
arXiv
44
citations
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
NEURIPS 2023
arXiv
34
citations
AIA: Autoregression-Based Injection Attacks Against Text2SQL Models
AAAI 2025
0
citations
