anssi-fr/ascad

How anssi-fr/ascad works

ASCAD is a side-channel-analysis benchmark and companion toolkit. The main workflow takes raw trace data and parameters to generate a labeled HDF5 database, trains a neural model on its profiling traces, then evaluates predictions on attack traces by ranking candidate AES key bytes. Documented campaign variants cover fixed- and variable-key ATMEGA traces and variable-key STM32 traces; multilabel generation and model evaluation are additional capabilities. The graph reflects the README and shown source excerpts; unsampled campaign-specific implementation details are not inferred.

Main entry points: ASCAD_test_models.py Evaluation runner · ASCAD_train_models.py Training runner · ASCAD_generate.py ASCAD generator · ATMEGA_AES_v1 ATMEGA campaigns

Components 17

Trace preparation

ASCAD generator ASCAD_generate.py
Trace labeling ASCAD_generate.py
ASCAD HDF5

Model training

Training runner ASCAD_train_models.py
ASCAD loader ASCAD_train_models.py
Neural architectures ASCAD_train_models.py
Model fitting ASCAD_train_models.py
Trained model

Attack evaluation

Evaluation runner ASCAD_test_models.py
Attack data loader ASCAD_test_models.py
Model predictions ASCAD_test_models.py
Key-byte ranking ASCAD_test_models.py
Rank plot ASCAD_test_models.py

Campaign datasets

ATMEGA campaigns ATMEGA_AES_v1
STM32 campaign STM32_AES_v2

Other components

Analyst
Raw trace HDF5

Connections 20

Analyst → ASCAD generator: runs with parameters Readme.md
Raw trace HDF5 → ASCAD generator: provides traces Readme.md
ASCAD generator → Trace labeling: extracts and labels ASCAD_generate.py
Trace labeling → ASCAD HDF5: writes profiling and attack sets ASCAD_generate.py
ATMEGA campaigns → Raw trace HDF5: campaign data Readme.md
STM32 campaign → Raw trace HDF5: campaign data Readme.md
Analyst → Training runner: runs with parameters Readme.md
ASCAD HDF5 → ASCAD loader: loads profiling traces ASCAD_train_models.py
Training runner → ASCAD loader: loads data ASCAD_train_models.py
Training runner → Neural architectures: selects architecture ASCAD_train_models.py
Training runner → Model fitting: starts fitting ASCAD_train_models.py
Model fitting → Trained model: saves model ASCAD_train_models.py
Analyst → Evaluation runner: runs with parameters Readme.md
Evaluation runner → Trained model: loads model ASCAD_test_models.py
Evaluation runner → Attack data loader: loads attack data ASCAD_test_models.py
ASCAD HDF5 → Attack data loader: provides attack traces ASCAD_test_models.py
Evaluation runner → Model predictions: predicts traces ASCAD_test_models.py
Evaluation runner → Key-byte ranking: computes key ranks ASCAD_test_models.py
Model predictions → Key-byte ranking: supplies probabilities ASCAD_test_models.py
Key-byte ranking → Rank plot: plots rank curve ASCAD_test_models.py

Drawn by GitDiagram on November 11, 2026 from the repository's file tree, README and source files. Read as Markdown ·