Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
Paper
•
2503.01865
•
Published
Conversational AI (CoAI) group from Tsinghua University
university
AI & ML interests
Dialogue Systems, Language Generation
Recent Activity
View all activity
thu-coai's activity
yangjunxiao2021
authored
a
paper
about 15 hours ago
chujiezheng
authored
a
paper
3 days ago
chujiezheng
authored
a
paper
6 days ago
Improve language tag
#1 opened 24 days ago
by
lbourdois
Improve language tag
#1 opened 24 days ago
by
lbourdois
JinfengZhou
updated
2
models
24 days ago
nucfusion
updated
2
models
25 days ago
JinfengZhou
published
2
models
27 days ago
Le-qi-LEI
updated
a
model
29 days ago
Le-qi-LEI
published
a
model
about 1 month ago
JinfengZhou
updated
a
model
about 2 months ago
nucfusion
updated
a
model
about 2 months ago
JinfengZhou
published
a
model
2 months ago
[bot] Conversion to Parquet
#1 opened 3 months ago
by
parquet-converter
Librarian Bot: Add language metadata for dataset
#2 opened 3 months ago
by
librarian-bot
yida-lu
updated
a
dataset
3 months ago
yida-lu
published
a
dataset
3 months ago