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 314 61

  2. AgentPoison AgentPoison Public

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

    Python 204 27

  3. DBA DBA Public

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

    Python 203 48

  4. 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.

    98 10

  5. VeriGauge VeriGauge Public

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

    C 90 7

  6. 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 85 8

Repositories

Showing 10 of 59 repositories
  • ShieldNet Public
    AI-secure/ShieldNet’s past year of commit activity
    JavaScript 0 0 0 0 Updated Mar 16, 2026
  • RedCode Public

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

    AI-secure/RedCode’s past year of commit activity
    Python 67 11 3 0 Updated Nov 14, 2025
  • SafeAuto Public

    [ICML 2025] SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

    AI-secure/SafeAuto’s past year of commit activity
    Python 25 2 5 0 Updated Jul 17, 2025
  • UDora Public

    [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents

    AI-secure/UDora’s past year of commit activity
    Python 31 5 1 0 Updated Jun 23, 2025
  • PolyGuard Public
    AI-secure/PolyGuard’s past year of commit activity
    Python 18 2 2 0 Updated Jun 17, 2025
  • AdvAgent Public
    AI-secure/AdvAgent’s past year of commit activity
    Jupyter Notebook 22 0 5 0 Updated May 28, 2025
  • 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 204 MIT 27 4 1 Updated Apr 12, 2025
  • MMDT Public

    Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models

    AI-secure/MMDT’s past year of commit activity
    Jupyter Notebook 27 2 1 0 Updated Mar 15, 2025
  • 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 57 Apache-2.0 17 1 0 Updated Jan 11, 2025
  • 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 13 MIT 0 1 0 Updated Oct 25, 2024