LOCK & ROLL: Deep-Learning Power Side-Channel Attack Mitigation using Emerging Reconfigurable Devices and Logic Locking
TimeTuesday, July 12th11:15am - 11:37am PDT
Location3006, Level 3
Hardware Security: Primitives, Architecture, Design & Test
DescriptionMany existing works have focused on mitigating the SAT attacks. We show that Power Side-Channel Attacks can retrieve the keys stored in the memory without simulating powerful SAT-attacks. To mitigate P-SCA and SAT-attack together, we propose a multi-layer defense mechanism called LOCK & ROLL: Deep-Learning Power Side-Channel Attack Mitigation using Emerging Reconfigurable Devices and Logic Locking. We proposed Magnetic Random-Access Memory (MRAM)-based Look Up Table called Symmetrical MRAM-LUT (SyM-LUT), which significantly reduces the standby energy consumption while masking the power side channel footprint. The LOCK & ROLL thwart many attacks including SAT-attack and deep learning-assisted P-SCA.