Skip to content
@safr-ai-lab

SAFR AI Lab @ Harvard

The Secure and Fair AI Lab at Harvard is led by @sethneel and Salil Vadhan. We study reliability, privacy, security, and bias in A.I.

Pinned Loading

  1. resources resources Public

    3

  2. survey-llm survey-llm Public

    A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code

    Python 56 8

Repositories

Showing 7 of 7 repositories
  • pandora-llm Public

    An extensible library for evaluating data extraction attacks and MIAs against LLMs. Developed as part of the pandora llm paper, linked below.

    safr-ai-lab/pandora-llm’s past year of commit activity
    Python 10 MIT 0 0 0 Updated Jul 18, 2024
  • survey-llm Public

    A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code

    safr-ai-lab/survey-llm’s past year of commit activity
    Python 56 8 0 0 Updated May 30, 2024
  • xai-disparity Public
    safr-ai-lab/xai-disparity’s past year of commit activity
    Jupyter Notebook 2 0 0 0 Updated May 13, 2024
  • resources Public
    safr-ai-lab/resources’s past year of commit activity
    3 0 0 0 Updated Apr 6, 2024
  • In-Context-Unlearning Public

    "In-Context Unlearning: Language Models as Few Shot Unlearners". Martin Pawelczyk, Seth Neel* and Himabindu Lakkaraju*; arXiv preprint: arXiv:2310.07579; 2023.

    safr-ai-lab/In-Context-Unlearning’s past year of commit activity
    Jupyter Notebook 3 0 0 0 Updated Oct 18, 2023
  • CounterfactualDistanceAttack Public

    "On the Privacy Risks of Algorithmic Recourse". Martin Pawelczyk, Himabindu Lakkaraju* and Seth Neel*. In International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, 2023.

    safr-ai-lab/CounterfactualDistanceAttack’s past year of commit activity
    Jupyter Notebook 0 0 0 0 Updated May 31, 2023
  • GerryFair Public Forked from sethneel/GerryFair

    Package implementing methods developed in "Preventing Fairness Gerrymandering" [ICML '18], "Rich Subgroup Fairness for Machine Learning" [ FAT* '19]. active development fork @algowatchupenn

    safr-ai-lab/GerryFair’s past year of commit activity
    Python 0 MIT 1 0 0 Updated Jan 3, 2019

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…