Skip to content
conftrace_
2025 ICML ICML 2025

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Tiansheng Huang, Gautam Bhattacharya, Pratik Joshi, Joshua Kimball, Ling Liu

Topics

Artificial Intelligence > Core AI > AI Safety Artificial Intelligence > Core AI > Responsible AI Artificial Intelligence > Core AI > Large Language Models

Keywords

transfer learning safety alignment fine-tuning attack large language model pruning harmful parameters
Download PDF