Code & Software
Open-source code, datasets, and software from Chen Hajaj and the Adaptive AI Lab at Ariel University.
Open-source code is hosted under the ArielCyber GitHub organization and chenhajaj’s GitHub.
Encrypted Traffic & Network Security
When a RF Beats a CNN and GRU
Code for comparing classical ML vs deep learning approaches for encrypted malware traffic classification.
Spectral Encrypted Internet Traffic Classification
Spectral methods for encrypted internet traffic classification.
PQClass
Classification of operating systems and browsers using post-quantum cryptography algorithms.
ITC Data Augmentations
Data augmentation techniques for internet traffic classification.
GAN N Net
GAN-based synthetic data generation for network traffic classification.
graph mux
Graph-based multiplexing for network traffic analysis.
TGN RCA
Official implementation: Uncovering Microservice Faults — Temporal Graph Approach to Root Cause Analysis.
OOD Is Not Magic
Out-Of-Distribution Is Not Magic: The Clash Between Rejection Rate and Model Success.
Frameworks, Pipelines & Utilities
OSF EIMTC
Open-source framework for encrypted internet and malicious traffic classification — full ML/DL pipeline, datasets, and benchmarks.
Embedder
Image embeddings from SOTA CV models (DINOv2, CLIP, SigLIP, ConvNeXt V2, EfficientNet V2).
API Security & Malware Detection
FT ANN
Classification-by-retrieval framework for few-shot anomaly detection to detect API injection attacks.
Android crystal ball
Code for: Crystal Ball — From Innovative Attack to Attack Effectiveness Classifier (IEEE Access, 2021).
robust malicious url detection
Malicious URL detection using a robust feature set resistant to adversarial example attacks.
When the guard failed the droid
Code for Android malware evasion case study.