Mechanical Phish: Resilient Autonomous Hacking

Yan Shoshitaishvili, Antonio Bianchi, Kevin Borgolte, Amat Cama, Jacopo Corbetta, Francesco Disperati, Audrey Dutcher, John Grosen, Paul Grosen, Aravind Machiry, Chris Salls, Nick Stephens, Ruoyu Wang, Giovanni Vigna

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The size and complexity of software is increasing, and security flaws are becoming more numerous, sophisticated, and impactful. While the vulnerability identification process (especially in hard-to-analyze binary programs) has traditionally been driven by highly skilled human analysts, this approach does not scale, given the vast amount of deployed software. Recently, the vulnerability analysis process has started to shift toward automated approaches. The DARPA Cyber Grand Challenge has played a key role in transforming disconnected research ideas into fully autonomous cyber reasoning systems that analyze code to find vulnerabilities, generate exploits to prove the existence of these vulnerabilities, and patch the vulnerable software. In this article, we discuss our cyber reasoning system, Mechanical Phish, which we have open-sourced; the lessons we learned in participating in this ground-breaking competition; and our system's performance as a tool in assisting humans during the DEF CON Capture-the-Flag competition, which followed the DARPA Cyber Grand Challenge.

Original languageEnglish (US)
Pages (from-to)12-22
Number of pages11
JournalIEEE Security and Privacy
Volume16
Issue number2
DOIs
StatePublished - Mar 1 2018

Fingerprint

vulnerability
Defects
process analysis
performance
software

Keywords

  • autonomous systems
  • computer aided analysis
  • computer security
  • Cyber Grand Challenge
  • Hacking without Humans
  • knowledge based systems
  • reasoning about programs
  • security

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Law

Cite this

Shoshitaishvili, Y., Bianchi, A., Borgolte, K., Cama, A., Corbetta, J., Disperati, F., ... Vigna, G. (2018). Mechanical Phish: Resilient Autonomous Hacking. IEEE Security and Privacy, 16(2), 12-22. https://doi.org/10.1109/MSP.2018.1870858

Mechanical Phish : Resilient Autonomous Hacking. / Shoshitaishvili, Yan; Bianchi, Antonio; Borgolte, Kevin; Cama, Amat; Corbetta, Jacopo; Disperati, Francesco; Dutcher, Audrey; Grosen, John; Grosen, Paul; Machiry, Aravind; Salls, Chris; Stephens, Nick; Wang, Ruoyu; Vigna, Giovanni.

In: IEEE Security and Privacy, Vol. 16, No. 2, 01.03.2018, p. 12-22.

Research output: Contribution to journalArticle

Shoshitaishvili, Y, Bianchi, A, Borgolte, K, Cama, A, Corbetta, J, Disperati, F, Dutcher, A, Grosen, J, Grosen, P, Machiry, A, Salls, C, Stephens, N, Wang, R & Vigna, G 2018, 'Mechanical Phish: Resilient Autonomous Hacking', IEEE Security and Privacy, vol. 16, no. 2, pp. 12-22. https://doi.org/10.1109/MSP.2018.1870858
Shoshitaishvili Y, Bianchi A, Borgolte K, Cama A, Corbetta J, Disperati F et al. Mechanical Phish: Resilient Autonomous Hacking. IEEE Security and Privacy. 2018 Mar 1;16(2):12-22. https://doi.org/10.1109/MSP.2018.1870858
Shoshitaishvili, Yan ; Bianchi, Antonio ; Borgolte, Kevin ; Cama, Amat ; Corbetta, Jacopo ; Disperati, Francesco ; Dutcher, Audrey ; Grosen, John ; Grosen, Paul ; Machiry, Aravind ; Salls, Chris ; Stephens, Nick ; Wang, Ruoyu ; Vigna, Giovanni. / Mechanical Phish : Resilient Autonomous Hacking. In: IEEE Security and Privacy. 2018 ; Vol. 16, No. 2. pp. 12-22.
@article{5efc233991734d008b47ef786207dfaa,
title = "Mechanical Phish: Resilient Autonomous Hacking",
abstract = "The size and complexity of software is increasing, and security flaws are becoming more numerous, sophisticated, and impactful. While the vulnerability identification process (especially in hard-to-analyze binary programs) has traditionally been driven by highly skilled human analysts, this approach does not scale, given the vast amount of deployed software. Recently, the vulnerability analysis process has started to shift toward automated approaches. The DARPA Cyber Grand Challenge has played a key role in transforming disconnected research ideas into fully autonomous cyber reasoning systems that analyze code to find vulnerabilities, generate exploits to prove the existence of these vulnerabilities, and patch the vulnerable software. In this article, we discuss our cyber reasoning system, Mechanical Phish, which we have open-sourced; the lessons we learned in participating in this ground-breaking competition; and our system's performance as a tool in assisting humans during the DEF CON Capture-the-Flag competition, which followed the DARPA Cyber Grand Challenge.",
keywords = "autonomous systems, computer aided analysis, computer security, Cyber Grand Challenge, Hacking without Humans, knowledge based systems, reasoning about programs, security",
author = "Yan Shoshitaishvili and Antonio Bianchi and Kevin Borgolte and Amat Cama and Jacopo Corbetta and Francesco Disperati and Audrey Dutcher and John Grosen and Paul Grosen and Aravind Machiry and Chris Salls and Nick Stephens and Ruoyu Wang and Giovanni Vigna",
year = "2018",
month = "3",
day = "1",
doi = "10.1109/MSP.2018.1870858",
language = "English (US)",
volume = "16",
pages = "12--22",
journal = "IEEE Security and Privacy",
issn = "1540-7993",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Mechanical Phish

T2 - Resilient Autonomous Hacking

AU - Shoshitaishvili, Yan

AU - Bianchi, Antonio

AU - Borgolte, Kevin

AU - Cama, Amat

AU - Corbetta, Jacopo

AU - Disperati, Francesco

AU - Dutcher, Audrey

AU - Grosen, John

AU - Grosen, Paul

AU - Machiry, Aravind

AU - Salls, Chris

AU - Stephens, Nick

AU - Wang, Ruoyu

AU - Vigna, Giovanni

PY - 2018/3/1

Y1 - 2018/3/1

N2 - The size and complexity of software is increasing, and security flaws are becoming more numerous, sophisticated, and impactful. While the vulnerability identification process (especially in hard-to-analyze binary programs) has traditionally been driven by highly skilled human analysts, this approach does not scale, given the vast amount of deployed software. Recently, the vulnerability analysis process has started to shift toward automated approaches. The DARPA Cyber Grand Challenge has played a key role in transforming disconnected research ideas into fully autonomous cyber reasoning systems that analyze code to find vulnerabilities, generate exploits to prove the existence of these vulnerabilities, and patch the vulnerable software. In this article, we discuss our cyber reasoning system, Mechanical Phish, which we have open-sourced; the lessons we learned in participating in this ground-breaking competition; and our system's performance as a tool in assisting humans during the DEF CON Capture-the-Flag competition, which followed the DARPA Cyber Grand Challenge.

AB - The size and complexity of software is increasing, and security flaws are becoming more numerous, sophisticated, and impactful. While the vulnerability identification process (especially in hard-to-analyze binary programs) has traditionally been driven by highly skilled human analysts, this approach does not scale, given the vast amount of deployed software. Recently, the vulnerability analysis process has started to shift toward automated approaches. The DARPA Cyber Grand Challenge has played a key role in transforming disconnected research ideas into fully autonomous cyber reasoning systems that analyze code to find vulnerabilities, generate exploits to prove the existence of these vulnerabilities, and patch the vulnerable software. In this article, we discuss our cyber reasoning system, Mechanical Phish, which we have open-sourced; the lessons we learned in participating in this ground-breaking competition; and our system's performance as a tool in assisting humans during the DEF CON Capture-the-Flag competition, which followed the DARPA Cyber Grand Challenge.

KW - autonomous systems

KW - computer aided analysis

KW - computer security

KW - Cyber Grand Challenge

KW - Hacking without Humans

KW - knowledge based systems

KW - reasoning about programs

KW - security

UR - http://www.scopus.com/inward/record.url?scp=85044852294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044852294&partnerID=8YFLogxK

U2 - 10.1109/MSP.2018.1870858

DO - 10.1109/MSP.2018.1870858

M3 - Article

AN - SCOPUS:85044852294

VL - 16

SP - 12

EP - 22

JO - IEEE Security and Privacy

JF - IEEE Security and Privacy

SN - 1540-7993

IS - 2

ER -