Furong Huang
Associate Professor @ University of Maryland
Home
Publications
Research
Project Page Highlights
Students
Teaching
Blog
Contact
Students on the Job Market
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Publications
Year
2025
Type(s)
Conference articles
Author(s)
Pankayaraj Pathmanathan and Udari Madhushani Sehwag and Michael-Andrei Panaitescu-Liess and Furong Huang
Source
In The AAAI-25 Workshop on Artificial Intelligence for Cyber Security, AICS 2025, 2025
Url
https://arxiv.org/abs/2410.11283
BibTeX
BibTeX
BibTeX
@inproceedings{pathmanathan2025advbdgenadversariallyfortified, title = {{AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment}}, author = {Pankayaraj Pathmanathan and Udari Madhushani Sehwag and Michael-Andrei Panaitescu-Liess and Furong Huang}, booktitle = {The AAAI-25 Workshop on Artificial Intelligence for Cyber Security, AICS 2025}, year = {2025}, url = {https://arxiv.org/abs/2410.11283}, note = {
arXiv
Code
Project page
},