Skip to content
@AI-secure

AI Secure

UIUC Secure Learning Lab

Popular repositories Loading

  1. DecodingTrust DecodingTrust Public

    A Comprehensive Assessment of Trustworthiness in GPT Models

    Python 266 57

  2. DBA DBA Public

    DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)

    Python 178 45

  3. Certified-Robustness-SoK-Oldver Certified-Robustness-SoK-Oldver Public

    This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular datasets and paper categorization.

    99 10

  4. VeriGauge VeriGauge Public

    A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]

    C 88 7

  5. InfoBERT InfoBERT Public

    [ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

    Python 83 7

  6. AgentPoison AgentPoison Public

    [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

    Python 74 5

Repositories

Showing 10 of 55 repositories
  • RedCode Public

    [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

    AI-secure/RedCode’s past year of commit activity
    Python 14 1 0 0 Updated Dec 10, 2024
  • AgentPoison Public

    [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

    AI-secure/AgentPoison’s past year of commit activity
    Python 74 MIT 5 4 0 Updated Dec 8, 2024
  • aug-pe Public

    [ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text

    AI-secure/aug-pe’s past year of commit activity
    Python 29 Apache-2.0 7 0 0 Updated Nov 12, 2024
  • AdvWeb Public
    AI-secure/AdvWeb’s past year of commit activity
    Jupyter Notebook 6 0 1 0 Updated Oct 30, 2024
  • FedGame Public

    Official implementation for paper "FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning" (NeurIPS 2023).

    AI-secure/FedGame’s past year of commit activity
    Python 5 MIT 0 1 0 Updated Oct 25, 2024
  • VFL-ADMM Public

    Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM (SaTML 2024)

    AI-secure/VFL-ADMM’s past year of commit activity
    Python 0 Apache-2.0 0 0 0 Updated Oct 21, 2024
  • DecodingTrust Public

    A Comprehensive Assessment of Trustworthiness in GPT Models

    AI-secure/DecodingTrust’s past year of commit activity
    Python 266 CC-BY-SA-4.0 57 11 2 Updated Sep 16, 2024
  • MMDT Public

    Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models

    AI-secure/MMDT’s past year of commit activity
    Jupyter Notebook 7 2 0 0 Updated Aug 13, 2024
  • helm Public Forked from stanford-crfm/helm

    Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

    AI-secure/helm’s past year of commit activity
    Python 0 Apache-2.0 260 0 2 Updated Jun 12, 2024
  • DPFL-Robustness Public

    [CCS 2023] Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks

    AI-secure/DPFL-Robustness’s past year of commit activity
    Python 6 0 0 0 Updated Feb 15, 2024
View all repositories

Most used topics

Loading…