Skip to content

@TrustAI TrustAI

Change the repository type filter

All

    Repositories list

    35 repositories

    • CROWD

      Public
      CROWD: Certified Robustness via Weight Distribution for Smoothed Classifiers against Backdoor Attack
      Python
      •0•0•0•0•Updated Dec 18, 2024Dec 18, 2024

    • ReCePS

      Public
      ReCePS: Reward Certification for Policy Smoothed Reinforcement Learning - AAAI 2024
      Jupyter Notebook
      •0•0•0•0•Updated Dec 18, 2024Dec 18, 2024

    • CertifyCMARL

      Public
      Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning - AAAI 2023
      Python
      •1•2•1•0•Updated Dec 16, 2024Dec 16, 2024

    • DeepSAVA

      Public
      DeepSAVA: Sparse Adversarial Video Attacks with Spatial Transformations - BMVC 2021 & Neural Networks (2023)
      Python
      •3•11•1•0•Updated Dec 13, 2024Dec 13, 2024

    • FAAL

      Public
      Towards Fairness-Aware Adversarial Learning - CVPR 2024
      Python
      •0•5•2•0•Updated Nov 6, 2024Nov 6, 2024

    • TARP-VP

      Public
      TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
      Python
      •0•0•0•0•Updated Oct 21, 2024Oct 21, 2024

    • LOAT

      Public
      Boosting Adversarial Training via Fisher-Rao Norm-based Regularization - CVPR 2024
      Python
      •0•1•0•0•Updated Jul 2, 2024Jul 2, 2024

    • ReRoGCRL

      Public
      ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning - AAAI 2024
      Python
      •0•0•0•0•Updated Jan 17, 2024Jan 17, 2024

    • SEAT

      Public
      SEAT: Self-adaptive Adversarial Training for Robust Medical Segmentation - MICCAI 2023
      Python
      •0•0•0•0•Updated Oct 16, 2023Oct 16, 2023

    • DeepGRE

      Public
      DeepGRE: Global Robustness Evaluation of Deep Neural Networks - ICASSP 2024
      0•0•0•0•Updated Sep 19, 2023Sep 19, 2023

    • NRAT

      Public
      NRAT: Towards Adversarial Training with Inherent Label Noise - Machine Learning Journal (2023)
      Python
      •1•2•0•0•Updated Jul 20, 2023Jul 20, 2023

    • GeoRobust

      Public
      Towards Verifying the Geometric Robustness of Large-scale Neural Networks - AAAI 2023
      Python
      •
      MIT License
      •3•6•0•0•Updated Jul 16, 2023Jul 16, 2023

    • SORA

      Public
      SORA: Scalable Black-box Reachability Analyser on Neural Networks - ICASSP 2023
      Python
      •
      MIT License
      •1•0•0•0•Updated Jun 5, 2023Jun 5, 2023

    • TextVerifer

      Public
      Towards Local Robustness Verification for Textual Classifiers with Certifiable Guarantees in Hamming Space - ACL 2023
      0•2•0•0•Updated May 2, 2023May 2, 2023

    • ODE4RobustViT

      Public
      Understanding Adversarial Robustness of Vision Transformers via Cauchy Problem - ECML 2022 & Software Impacts (2023)
      Python
      •
      MIT License
      •4•5•0•0•Updated Apr 2, 2023Apr 2, 2023

    • DIMBA

      Public
      DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking - Machine Learning Journal (2022)
      Python
      •0•4•2•0•Updated Dec 8, 2022Dec 8, 2022

    • DeepNNC

      Public
      Reachability Analysis of Neural Network Control Systems - AAAI 2023
      0•4•0•0•Updated Dec 1, 2022Dec 1, 2022

    • PRoA

      Public
      PRoA: A Probabilistic Robustness Assessment against Functional Perturbations - ECML 2022
      Python
      •0•1•1•0•Updated Nov 27, 2022Nov 27, 2022

    • GUAP

      Public
      Generalizing Universal Adversarial Attacks Beyond Additive Perturbations - ICDM 2020 & Machine Learning Journal (2023)
      Jupyter Notebook
      •5•9•0•0•Updated Nov 27, 2022Nov 27, 2022

    • 3DVerifier

      Public
      3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models - Machine Learning Journal (2022)
      Python
      •0•0•0•0•Updated Nov 27, 2022Nov 27, 2022

    • DEAT

      Public
      Dynamic Efficient Adversarial Training Guided by Gradient Magnitude - TEA@NeurIPS 2022
      Python
      •
      MIT License
      •0•2•0•0•Updated Nov 27, 2022Nov 27, 2022

    • tutorial

      Public
      IJCAI Tutorial on Adversarial Robustness of Deep Learning - IJCAI 2021
      HTML
      •0•0•0•0•Updated Jul 23, 2022Jul 23, 2022

    • AdversarialDetection

      Public
      Falsification Tool for Assessing Robustness of End-to-End Object Detection Systems
      Python
      •3•0•0•0•Updated Jan 10, 2022Jan 10, 2022

    • AdversarialDriving

      Public
      Falsification Tool for Assessing Robustness of End-to-End Autonomous Driving Systems
      Python
      •2•7•0•0•Updated Jan 10, 2022Jan 10, 2022

    • DeepTRE

      Public
      DeepTRE (Tensor-based Robustness Evaluation of DNNs for the Hamming Distance) - IJCAI 2019
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •0•0•0•0•Updated Nov 22, 2021Nov 22, 2021

    • DeepConcolic

      Public
      Concolic Testing for Deep Neural Networks
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •45•117•4•1•Updated Jul 16, 2021Jul 16, 2021

    • DeepGame

      Public
      A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •8•20•1•0•Updated Dec 16, 2020Dec 16, 2020

    • testRNN

      Public
      Coverage-Guided Testing of Long Short-Term Memory (LSTM) Networks
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •14•18•0•0•Updated Dec 15, 2020Dec 15, 2020

    • DeepQuant

      Public
      Quantifying the Robustness of Deep Neural Networks - Complex & Intelligent Systems
      MATLAB
      •0•2•0•0•Updated Aug 21, 2020Aug 21, 2020

    • wami-detector-verification

      Public
      Reliability Validation of a Learning-Enabled System -- WAMI Tracking
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •0•0•0•0•Updated Mar 2, 2020Mar 2, 2020