FHEON Studio
Use encrypted neural networks live through our FHEON Studio.
Project site: FHEON Studio
Source: GitHub
The pages are Workbench, Build and Runs.
Workbench
The Workbench runs a FHEON program on test images in five choices and a model:
Task: inference or training.
Primitives: standard or diagonal (Standard Primitives, Diagonal Primitives (FHEON-D)). Training uses the standard layout.
Input: single input or batch (standard primitives).
Dataset: MNIST, CIFAR-10 or CIFAR-100. Every model runs on the dataset it was trained on.
Security: the performance-efficient parameters (not a standard level) or 128 / 192 / 256-bit security (
-DSECURITY_LEVEL, one build folder each:build/,build/std128/, …). The batch programs and the LeNet-5 diagonal programs use every slot of the larger ring of a standard level (HEConfig.fillSlots): a batch then takes more images (32 instead of 16 at 128 bits for the2^14-slot programs, see Batch Input Examples), and the run panel and the model details show the ring, slots and batch of the chosen level, and programs that only repeat another one at that level are not listed (see Security Levels, Ring Dimension and Packing). The keys of a standard level are kept in<program>-<mode>-std<level>-<digest>, the digest of the program’s CKKS settings, so keys of older parameters are never loaded.
The models are the programs of FHEON:
Programs |
Execution |
Folder |
|---|---|---|
Standard, single input |
sequential |
|
Diagonal, single input |
sequential |
|
Standard, batch |
multithreaded |
|
Training |
multithreaded |
|
Each program has one execution mode: the single-input programs run sequentially, the batch programs and the training
multithreaded (with the program’s default number of workers, --threads). The model card shows the network, the CKKS
parameters, reference timings and the build status; a program that is not built at the chosen security level is
compiled first, as part of the run. Then pick the test images (any images for single-input programs; a
ready-made window or a batch built image by image for batch programs), or upload images of your own in the format of the
dataset, and run.
Build
Build compiles the targets of CMakeLists.txt with the chosen security level, build folder, build type, task,
primitives, input, model and batch size, and shows the CMake commands it runs. Builds run one at a time and keep their
log in frontend/builds/. Test runs run the first image (or batch) of any built program, and System shows the
FHEON checkout, the build folders and the datasets the Studio uses.
Runs
The run page follows a run in the order the programs work: context and keys, weights, then read, normalize and encrypt,
evaluate and decrypt for each image (once for a batch). It shows the progress of every layer, the latest operations, the
decrypted scores of each image, the totals (time per image, bootstrapping time, peak memory), the CKKS parameters and the
console. The Runs list keeps the history with accuracy, time per image, peak memory and total time; every run keeps
console.log, fhepredictions.txt and job.json in frontend/runs/<id>/.
Configuration
frontend/backend/studio.config.json (from studio.config.example.json) or environment variables:
Variable |
Default |
Meaning |
|---|---|---|
|
two folders above |
the FHEON checkout |
|
|
build folders and their security level |
|
|
keys, one folder per program |
|
|
parent of the training programs’ parameters |
|
|
runs at the same time (encrypted runs are memory-bound) |
The API is documented by the backend itself at /api/docs.