TESSERACT

Framework for fair and sound evaluations of ML classifiers.

News

  • Jan 2019: TESSERACT accepted at USENIX Security 2019.
  • Oct 2018: Talk on TESSERACT accepted for USENIX Enigma 2019! More details soon.
  • Oct 2018: We are presenting our poster on TESSERACT's implementation at ACM CCS 2018.
    See you in Toronto, Canada!

Access

We are hosting TESSERACT code on a private Bitbucket repository, under open source license. To get access to the repository, please complete the following form: We have already granted access to people from the following institutions (alphabetical order):
  1. ANSSI - the French Network and Information Security Agency
  2. Boise State University, USA
  3. Birla Institute of Technology and Science, Pilani, India
  4. Capital One, USA
  5. Carnegie Mellon University, USA
  6. Czech Technical University, Czech Republic
  7. Deakin University, Australia
  8. Federal University of Paraná (UFPR), Brazil
  9. Georgia Tech, USA
  10. Huazhong University of Science and Technology (HUST), China
  11. King's College London, UK
  12. TU Dublin, Institute of Technology Blanchardstown, Ireland
  13. Nanjing University, Software Institute, China
  14. National Institute of Technology, Rourkela, India
  15. New York University, USA
  16. Northwest University, China
  17. Osaka University, Japan
  18. Rice University, USA
  19. Royal Holloway, University of London, UK
  20. Institute for Information Industry, Taiwan
  21. SnT - University of Luxembourg
  22. Swinburne University of Technology, Australia
  23. The Interdisciplinary Center Herzliya (IDC), Israel
  24. The MITRE Corporation, USA
  25. Tsinghua University, China
  26. TU Braunschweig, Germany
  27. TU Munich, Germany
  28. Universidad Carlos III de Madrid, Spain
  29. University of Cagliari, Italy
  30. University of Jinan, China
  31. University of New South Wales, Australia
  32. University of Toronto, Canada
  33. VIT Bhopal, India
  34. Washington State University, USA

Papers

TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time
Feargus Pendlebury*, Fabio Pierazzi*, Roberto Jordaney, Johannes Kinder, and Lorenzo Cavallaro
USENIX Sec · 28th USENIX Security Symposium, 2019
@inproceedings{pendlebury2019tesseract,
author = {Feargus Pendlebury*, Fabio Pierazzi*, Roberto Jordaney, Johannes Kinder, and Lorenzo Cavallaro},
title = {{TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time}},
booktitle = {28th USENIX Security Symposium},
year = {2019},
address = {Santa Clara, CA},
publisher = {USENIX Association},
note = {USENIX Sec}
}
POSTER: Enabling Fair ML Evaluations for Security
Feargus Pendlebury*, Fabio Pierazzi*, Roberto Jordaney, Johannes Kinder, Lorenzo Cavallaro
ACM CCS · 25th ACM Conference on Computer and Communications Security, 2018

Talks

Fabio Pierazzi presents TESSERACT at USENIX Security 2019.
Lorenzo Cavallaro gives a preview of the work at USENIX Enigma 2019.

People

  • Feargus Pendlebury, Ph.D. Student, King's College London & Royal Holloway, University of London
  • Fabio Pierazzi, Lecturer (Assistant Professor), King's College London.
  • Roberto Jordaney, Research Engineer, HP Labs, Bristol, UK
  • Johannes Kinder, Full Professor of Computer Science, Bundeswehr University Munich, Germany
  • Lorenzo Cavallaro, Full Professor of Computer Science, Chair in Cybersecurity (Systems Security), King's College London