Last updated
Last updated
This challenge is a deep learning-based side-channel analysis contest hosted by from Nanyang Technological University. This is part of the .
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!
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.
As in previous challenges, participants can join in the following way:
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:
A provided EM trace dataset (~250K 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 a potential cash award.
The dataset will be made available at:
Coming Soon!!
Jump right in
