In this project we have extended the original [**gr-tempest**](https://github.com/git-artes/gr-tempest) (a.k.a. [Van Eck Phreaking](https://en.wikipedia.org/wiki/Van_Eck_phreaking) or simply TEMPEST; i.e. spying on a video display from its unintended electromagnetic emanations) by using deep learning to improve the quality of the spied images. See an illustrative diagram above. Some examples of the resulting inference of our system and the original unmodified version of gr-tempest below.
We are particularly interested in recovering the text present in the display, and we improve the Character Error Rate from 90% in the unmodified gr-tempest, to less than 30% using our module. Watch a video of the full system in operation:
In addition to the source code, we are also opne sourcing the whole dataset we used. Follow [this dropbox link](https://www.dropbox.com/scl/fi/7r2o8nbws45q30j5lkxjb/deeptempest_dataset.zip?rlkey=w7jvw275hu8tsyflgdkql7l1c&st=e8rdldz0&dl=0) to download a ZIP file (~7GB). After unzipping, you will find synthetic and real captured images used for experiments, training, and evaluation during the work. These images consists of 1600x900 resolution with the SDR's center frequency at the third pixel-rate harmonic (324 MHz).
Both [gr-tempest](./gr-tempest/) and [end-to-end](./end-to-end/) folders contains a guide on how to execute the corresponding files for image capturing, inference and train the deep learning architecture based on DRUNet from [KAIR image restoration repository](https://github.com/cszn/KAIR/tree/master).
The code is written in Python version 3.10, using Anaconda environments. To replicate the working environment, create a new one with the libraries listed in [*requirements.txt*](./requirements.txt):
Regarding installations with GNU Radio, **it is necessary to use the [gr-tempest](./gr-tempest/) version in this repository***(which contains a modified version of the original gr-tempest)*. After this, run the following *grc* files flowgraphs to activate the *hierblocks*:
Finally run the flowgraph [deep-tempest_example.grc](./gr-tempest/examples/deep-tempest_example.grc) to capture the monitor images and be able to recover them with better quality using the *Save Capture* block.