Skip to content
conftrace
_
Papers
Trends
Conferences
Explore
More
Authors
Topics
Keywords
Insights
Papers
Trends
Conferences
Explore
Authors
Topics
Keywords
Insights
Achievements
Home
›
Keywords
›
outlier samples
outlier samples
1 paper
Explore in graph
Co-occurring keywords
· papers mentioning both
alignment safeguards
(1)
self-inf-n
(1)
safety degradation
(1)
large language model
(1)
fine tuning
(1)
Papers
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
ICML 2025
<
1
>