Skip to content
View boyiwei's full-sized avatar
🤡
🤡

Highlights

  • Pro

Organizations

@princeton-polaris-lab

Block or report boyiwei

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. princeton-polaris-lab/Dynamic-Risk-Assessment princeton-polaris-lab/Dynamic-Risk-Assessment Public

    [NeurIPS 2025 D&B] Dynamic Risk Assessment for Offensive Cybersecurity Agents

    Python 8

  2. scaleapi/BioRiskEval scaleapi/BioRiskEval Public

    open source codebase for BioRiskEval

    Jupyter Notebook 8 2

  3. alignment-attribution-code alignment-attribution-code Public

    [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

    Python 91 17

  4. CoTaEval CoTaEval Public

    [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models

    Python 17 6

  5. princeton-polaris-lab/Evaluating-Durable-Safeguards princeton-polaris-lab/Evaluating-Durable-Safeguards Public

    [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs

    Python 13 1

  6. princeton-pli/hal-harness princeton-pli/hal-harness Public archive

    Python 311 63