A Hacker Guide To Deep-Learning Based Side Channel Attacks

Presented at DEF CON 27 (2019), Aug. 9, 2019, 2 p.m. (45 minutes).

This talk explores how AI is revolutionizing hardware side-channel attacks and what this new wave of attacks mean for the future of hardware cryptography. Based on the lessons learned while successfully attacking many hardware AES implementations using deep-learning this talk discuss why those attacks are fundamentally more efficient and details how to conduct then in practice.

Presenters:

• Elie Bursztein - Google
  Elie Bursztein leads Google' security & anti-abuse research team. He has authored over fifty research papers in the field for which he was awarded 6 best papers awards and multiple industry distinctions including the Black Hat pwnie award. Born in Paris, he received a Ph.D from ENS-cachan in 2008 before working at Stanford University and ultimately joining Google in 2011. Twitter @elie Website: https://elie.net
• Jean-Michel Picod - Google   as Jean Michel Picod
  Jean-Michel Picod is currently working at Google Switzerland. He holds an engineering degree in computer systems, networks and security. He has contributed on several open source projects (GoodFET, pynids, etc.) and published several open source tools such as DPAPIck, OWADE, scapy-radio, forensic scripts, Twitter: @jmichel_p Website: https://www.j-michel.org/

Links:

• https://defcon.org/html/defcon-27/dc-27-speakers.html#Bursztein
• https://infocon.org/cons/DEF CON/DEF CON 27/DEF CON 27 video and slides/DEF CON 27 - Elie Bursztein - How Deep Learning Is Revolutionizing Side-Channel Cryptanalysis.mp4
• https://infocon.org/cons/DEF CON/DEF CON 27/DEF CON 27 video and slides/DEF CON 27 - Elie Bursztein - How Deep Learning Is Revolutionizing Side-Channel Cryptanalysis.srt (subtitles)
• https://www.youtube.com/watch?v=QXTricqAtPk

Similar Presentations:

• Black Hat USA 2018 / Lowering the Bar: Deep Learning for Side Channel Analysis
• DEF CON 28 (2020) Virtual / A Hacker's Guide to Reducing Side-Channel Attack Surfaces Using Deep-Learning
• Black Hat USA 2020 Virtual / A Hacker's Guide to Reducing Side-Channel Attack Surfaces Using Deep-Learning