Raphael Labaca Castro M.Sc.

Raphael Labaca Castro M.Sc.
CODE
Gebäude Carl-Wery-Str. 18, Zimmer 1604
+49 89 6004-7317
raphael.labaca@unibw.de

Raphael Labaca Castro M.Sc.

 

Interests:

 I have been working for a few years in the security industry, particularly with malware, before starting my PhD at CODE. Currently, I am working on adversarial learning with malware classifiers. I am interested in understanding different approaches that can lead to malware misclassification and how to better protect neural networks in general against these attacks.

 

Publications:

  • R. Labaca Castro, B. Biggio, G. Dreo Rodosek: Attacking Malware Classifiers by Crafting Gradient-Attacks that Preserve Functionality. ACM 26th Conference on Computer and Communications Security (CCS), London, United Kingdom, November 12, 2019
  • R. Labaca Castro, C. Schmitt, G. Dreo Rodosek: AIMED: Evolving Malware with Genetic Programming to Evade Detection. IEEE 18th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Rotorua, New Zealand, August 6, 2019 
  • R. Labaca Castro, C. Schmitt, G. Dreo Rodosek: Training GANs to Generate Adversarial Examples Against Malware Classification. 40th IEEE Symposium on Security and Privacy (S&P), San Francisco, CA, USA, May 20, 2019 
  • R. Labaca Castro, C. Schmitt, G. Dreo Rodosek: ARMED: How Automatic Malware Modifications Can Evade Static Detection? 5th International Conference on Information Management (ICIM), Cambridge, UK, March 2019. Best Presentation Award
  • R. Labaca Castro, C. Schmitt, G. Dreo: Genetic Programming to Evade Static Malware Detection. Annual Computer Security Applications Conference (ACSAC), San Juan, Puerto Rico, USA, December 6, 2018
  • C. Dietz, R. Labaca Castro, J. Steinberger, C. Wilczak, M. Antzek, A. Sperotto, A. Pras: IoT-Botnet Detection and Isolation by Access Routers. 9th International Conference on the Network of the Future (NoF), Poznan, Poland, November 2018
  • R. Labaca Castro, G. Dreo Rodosek: Black Box Attacks using Adversarial Samples against Machine Learning Malware Classification to Improve Detection. 12th International Conference on Autonomous Infrastructure, Management, and Security (AIMS), Munich, Germany, June 2018