Automating Safety Enhancement for LLM-based Agents with Synthetic Risk Scenarios
Paper
•
2505.17735
•
Published
•
3
•
1
Zhou Xueyang
zhouxueyang
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via
Objective-Decoupled Optimization
commented on
a paper
5 days ago
Automating Safety Enhancement for LLM-based Agents with Synthetic Risk
Scenarios
commented on
a paper
6 days ago
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via
Objective-Decoupled Optimization
Organizations
None yet
zhouxueyang's activity
commented
a
paper
5 days ago