Research interests include adversarial machine learning, deep learning, large-scale malware classification, active learning, and early time-series classification.
Saturday at in 101 Track 45 minutes | Demo, Tool Follow me on a journey where we p0wn one of the most secure platforms on earth.
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.
Hyrum Anderson Hyrum Anderson is technical director of data scientist at Endgame, where he leads research on detecting adversaries and their tools using machine learning.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).In an analogous fashion, we demonstrate an AI agent that has learned through thousands of "games" against a next-gen AV malware detector which sequence of functionality-preserving changes to perform on a Windows PE malware file so that it bypasses the detector.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.