# Overview

## Welcome to GE Wars: The Deep Learning SCA battle! 

This challenge is a deep learning-based side-channel analysis contest hosted by [PACE@TL](https://pace-tl-ntu.github.io/) from Nanyang Technological University. This is part of the [CHES 2025 challenge](https://ches.iacr.org/2025/challenge.php). 

Since 2015, CHES has hosted annual crypto-engineering challenges pushing the boundaries of applied cryptographic research. The 2025 edition introduces a new Deep Learning Side-Channel Analysis (DL-SCA) challenge targeting a real-world AES implementation! Think your model can recover secret keys from noisy electromagnetic traces? Want to benchmark your DL-SCA techniques against the community? This challenge is for you!<br>

The CHES 2025 SCA Challenge focuses on profiled attacks (template or deep learning-based) against an unprotected AES-C implementation running on a Raspberry Pi 4B. This introduces jitter and noise, raising the bar for traditional attack strategies and inviting novel DL-based solutions.<br>

As in previous challenges, participants can join in the following way:<br>

* Attackers develop models to extract the secret key using fewer traces than the provided baseline.

The challenge runs from **June 15 to August 15, 2025** and includes:<br>

* A provided EM trace dataset (500K profiling, 100K attack traces)
* A shared task: Recovering one AES S-box output byte with minimal traces (using Guessing Entropy)
* Continuous public leaderboard
* Final results and possible **Rump Session spotlight at CHES 2025**

Winners **earn recognition in the community**—and **cash award.**

### Winners

Thank you everyone who participated! We have concluded the challenges!\
Congrats to the winners:&#x20;

1. **Team MarsVisitor:** \
   Xingyu Xie, Yingte Xu, Zhiyuan Zhang (Max Planck Institute for Security and Privacy, Germany)\
   [Code](https://drive.google.com/file/d/1GNTm-ipJb7I1Y4oByJkOvwhTBAi47wbF/view?usp=drive_link), [Video](https://drive.google.com/file/d/1kQ9qIMOB8WB2FNrt2JwTZ47NuDB3mz0X/view?usp=drive_link), [PDF](https://drive.google.com/file/d/1uNdVp0gBT9I7BM14TF8kTmkKj-EQ7qaL/view?usp=drive_link), [Github](https://github.com/LucianoXu/CHES2025-Challenge)
2. **Team transit method:** \
   Aron Gohr (Independent Researcher), Friederike Laus (BSI, Germany)\
   [Code](https://drive.google.com/file/d/11qAdUJ6HjNrCm9Vw8PGa6y4Z3_p4CB6K/view?usp=drive_link), [Video](https://drive.google.com/file/d/17tVlD8698BAeE3b6MhdngChuj49iZHPc/view?usp=drive_link), [Slides](https://drive.google.com/file/d/1o91ivGTqkVDoVzxxrLO2rJHkV_bCgoRB/view?usp=drive_link)
3. **Team Kaito Leak**:\
   Xin Zhang, Xiaolei Shi, Qingni Shen, Yuhui Zhang, Chang Liu (Peking University, China) \
   [Code](https://drive.google.com/file/d/1UmSjuALnDwxKe9PHT4aixMD9gQ_Bd1G1/view?usp=drive_link), [Video](https://drive.google.com/file/d/1P_QeIm-8LW6VepWIvKOU4QXlogNKQcQa/view?usp=drive_link)

The ppt slides used during the Rump Session at CHES 2025 can be found here: [pptx](https://docs.google.com/presentation/d/11AEQ4v9ZrFMCpTYA6DnKp_Ak4JG9fXB-/edit?usp=drive_link\&ouid=118383905112624015155\&rtpof=true\&sd=true).

### Datasets

The datasets are now made available at the following links: [public dataset](https://drive.google.com/drive/folders/1JGbphwZXQvN_tEhpBIbQ-q-pN9wkqKQ-?usp=sharing)  and [private dataset](https://drive.google.com/drive/folders/1foaYhR_40_s17vmOdEv0dhKFVB09qksc?usp=drive_link).

### Citation

If our dataset contributed to your research, please acknowledge it with the following citation:

```
@misc{ge_wars2025,
author = {Shivam Bhasin and Harishma Boyapally and Dirmanto Jap and Trevor Yap and Qianmei Wu.},
title = {{GE Wars: The Deep Learning SCA battle}},
howpublished    = {CHES Challenge 2025},
year      = {2025},
note = {https://pace-tl.gitbook.io/ches-challenge-2025}
}
```

{% hint style="info" %}
The contributors involved in this project are Shivam Bhasin, Harishma Boyapally, Dirmanto Jap, Trevor Yap and Qianmei Wu.<br>
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://pace-tl.gitbook.io/ches-challenge-2025/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.