Boyi Wei
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Dynamic Risk Assessments for Offensive Cybersecurity Agents
arXiv 2025
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
arXiv 2025
On Evaluating the Durability of Safeguards for Open-Weight LLMs
arXiv 2024
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers