🔖 Release Notes This patch release finalizes the repository for integration with Zenodo, generating a permanent Digital Object Identifier (DOI) for academic citation. 🔄 What's New in v1.0.1 Zenodo Integration: Configured repository metadata for permanent archiving. Documentation: Added status badges (DOI, License) to the README.md. Stability: Codebase is frozen to match the manuscript submission state. 📖 Framework Overview The Adversarial Robustness Evaluation of AI IDS Framework provides a reproducible pipeline to evaluate the robustness of Machine Learning (Random Forest, Logistic Regression) and Deep Learning (MLP, CNN-1D) Intrusion Detection Systems against adversarial attacks under realistic black-box transfer conditions. Key Features End-to-End Preprocessing: Automated cleaning, normalization, and stratified splitting (70/10/20) for CICIDS2017 and CICIDS2018 datasets. Model Training: Scripts to train and evaluate: Baselines: Random Forest (RF), Logistic Regression (LR). Deep Learning: Multilayer Perceptron (MLP), 1D-CNN. Surrogate Models: Independent shadow models for black-box attack generation. Adversarial Attack Suite: Implementation of four attack families with Semantic Constraints (feature validity enforcement): Gradient-Based: FGSM, PGD ($L_{\infty}$ norm). Black-Box: HopSkipJump (HSJA), Zeroth-Order Optimization (ZOO). Cross-Dataset Evaluation: Tools to test the transferability of adversarial examples from CICIDS2017 to the CICIDS2018 Friday slice. Quick Start Clone the repository: git clone [https://github.com/YourUsername/IDS-Adversarial-Robustness.git](https://github.com/sameroudi/adversarial-evaluation-ai-ids.git) Install dependencies: pip install -r requirements.txt Run the pipeline: # 1. Preprocess Data python scripts/prepare_cicids2017.py # 2. Train Models python scripts/train_deep_cicids2017.py # 3. Execute Attacks python scripts/run_attacks_cicids2017.py Citation Please cite the software using the generated DOI: Aoudi, S. (2025). Adversarial Robustness Evaluation of AI IDS Framework (v1.0.1) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.17999876