Boyi Wei
Source-listed: PhD student / PhD candidate · Princeton University
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Dynamic Risk Assessments for Offensive Cybersecurity AgentsSaved credit: Contributor · 2025Explore people connected to this work →
- Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank ModificationsSaved credit: Contributor · 2024Explore people connected to this work →
- Evaluating Copyright Takedown Methods for Language ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- On Evaluating the Durability of Safeguards for Open-Weight LLMsSaved credit: Contributor · 2025Explore people connected to this work →
- An Adversarial Perspective on Machine Unlearning for AI SafetySaved credit: Contributor · 2024Explore people connected to this work →