Using Deep Learning Attribution Methods for Fault Injection Attacks
Black Hat Asia 2025 · Day 1 · Briefings
In a compelling presentation at Black Hat Asia, Karim, a Hardware Security Expert from Ledger's Dungeon security research team, unveiled a novel approach to significantly enhance the efficacy of **fault injection attacks (FIA)** against secure hardware. The talk, titled "Using Deep Learning Attribution Methods for Fault Injection Attacks," demonstrated how **deep learning (DL) attribution methods**, traditionally employed in side-channel analysis, can be repurposed to reverse-engineer the execution flow of black-box chips, thereby identifying precise timing windows for injecting faults. This methodology dramatically reduces the time and effort typically associated with brute-force fault injection, transforming a laborious, months-long endeavor into a targeted, efficient attack.
AI review
Karim from Ledger's Dungeon team delivered a groundbreaking presentation that marries deep learning attribution with fault injection attacks, fundamentally transforming black-box hardware exploitation. By intelligently repurposing DL to precisely identify vulnerable timing windows, he demonstrated a targeted double-fault attack on an Analog Devices secure authenticator, bypassing its double-verification countermeasure. This research sets a new, higher standard for hardware security evaluation, unequivocally demanding that defenders integrate ML expertise to counter these sophisticated…