Targeted Vaccine: Safety Alignment for Large Language Models Against Harmful Fine-Tuning via Layer-Wise Perturbation
| Title: | Targeted Vaccine: Safety Alignment for Large Language Models Against Harmful Fine-Tuning via Layer-Wise Perturbation |
|---|---|
| Authors: | Liu, G.; Lin, W.; Mu, Q.; Huang, T.; Mo, R.; Tao, Y.; Shen, L. |
| Source: | IEEE Transactions on Information Forensics and Security IEEE Trans.Inform.Forensic Secur. Information Forensics and Security, IEEE Transactions on. 20:10806-10817 2025 |
| Database: | IEEE Xplore Digital Library |