0 0ctane 0x00string A Aleph-Naught- Hyrum Anderson Ayoul3 Dor Azouri B Leonard Bailey (1, 2) Avi Bashan Ryan Baxendale Max Bazaliy Oleksandr Bazhaniuk Scott Behrens B1TKILL3R Steinthor Bjarnason Hanno Böck Daniel Bohannon (DBO) Francis Brown Elie Bursztein Shabid Buttar C Caezar Nick Cano Nate Cardozo Damien "virtualabs" Cauquil ceyx chaosdata Cheng CINCVol FLT CJ_000 Gil Cohen Tomer Cohen Romain Coltel Joshua Corman (1, 2) Dan Cvrcek D Christian "quaddi" Dameff MD MS Josh Datko Dark Tangent (1, 2) Patrick De Santis Andreas Dewes Roger Dingledine Cory Doctorow Christopher Domas E Chris Eagle Svea Eckert Omar Eissa El Kentaro Peyton "Foofus" Engel F Allan Friedman Joe Fitz Patrick Gus Fritschie Fuzzy Nop G Eva Galperin Denton Gentry ginsback Igal Gofman Chris Grayson Grifter H Jason Haddix Hawaii John Weston Hecker Jeremy Heffner Jason Hernandez High Wiz Kashmir Hill Lee Holmes (1, 2) Lin Huang Stephan Huber Rep.
Less well appreciated, however, is that machine learning can be susceptible to attack by, ironically, other machine learning models.
In this talk, we demonstrate an AI agent trained through reinforcement learning to modify malware to evade machine learning malware detection.
Embedded technologies like Intel Management Engine pose significant threats when, not if, they get exploited.
Advanced attackers in possession of firmware signing keys, and even potential access to chip fabrication, could wreak untold havoc on cryptographic devices we rely on.
Suzanne Schwartz (1, 2) Nathan Seidle Shaggy Haoqi Shan Mickey Shkatov Eden Shochat Marina Simakov skud Sky Dimitry Snezhkov Mikhail Sosonkin John Sotos S0ups space B0x Jason Staggs Gerald Steere Jayson E.
Street Suggy Matt Suiche T TBA Evan Teitelman Richard Thieme Chris Thompson trixr4skids Orange Tsai Jeff "r3plicant" Tully MD Philip Tully V Ilja van Sprundel [email protected] W Kit Walsh Patrick Wardle (1, 2) Waz Wiseacre Matt Wixey Beau Woods X Xlogic X Y Luke Young Jian Yuan Zhang Yunhai Z Zardus Sarah Zatko Zenofex zerosum0x0 Min (Spark) Zheng Sunday at in Track 4 20 minutes | Demo, Tool Modern computing platforms offer more freedom than ever before.
After surveying all-too-possible low level attacks on critical systems, we will introduce an alternative open source solution to peace-of-mind cryptography and private computing.
By using programmable logic chips, called Field Programmable Gate Arrays, this device is more open source than any common personal computing system to date.
Reinforcement learning has produced game-changing AI's that top human level performance in the game of Go and a myriad of hacked retro Atari games (e.g., Pong).