Machine Learning Power Side-Channel Attack on SNOW-V
By: Deepak , Rahul Balout , Anupam Golder and more
Potential Business Impact:
Breaks secret codes used in 5G phones.
This paper demonstrates a power analysis-based Side-Channel Analysis (SCA) attack on the SNOW-V encryption algorithm, which is a 5G mobile communication security standard candidate. Implemented on an STM32 microcontroller, power traces captured with a ChipWhisperer board were analyzed, with Test Vector Leakage Assessment (TVLA) confirming exploitable leakage. Profiling attacks using Linear Discriminant Analysis (LDA) and Fully Connected Neural Networks (FCN) achieved efficient key recovery, with FCN achieving > 5X lower minimum traces to disclosure (MTD) compared to the state-of-the-art Correlational Power Analysis (CPA) assisted with LDA. The results highlight the vulnerability of SNOW-V to machine learning-based SCA and the need for robust countermeasures.
Similar Papers
Power Side-Channel Analysis of the CVA6 RISC-V Core at the RTL Level Using VeriSide
Cryptography and Security
Finds secret codes hidden in computer chips.
It's Not Just a Phase: On Investigating Phase Transitions in Deep Learning-based Side-channel Analysis
Cryptography and Security
Lets us see inside secret computer attacks.
Real-world Edge Neural Network Implementations Leak Private Interactions Through Physical Side Channel
Cryptography and Security
Steals secrets from devices using invisible signals.