TUM Logo

Bojan Kolosnjaji

Bojan Kolosnjaji

Alumni

E-Mail:

Research Interests

I do research in the area of machine learning and its applications in IT security, but also in designing robust machine learning systems.

I am currently participating in the SPARTA EU H2020 Project. Previously I was active in the IUNO project and the FORSEC research alliance.

Topics of special interest:

  • adversarial learning
  • anomaly detection under resource constraints
  • large-scale malware detection and analysis using machine learning methods (neural networks, topic modeling, kernel methods)
  • general machine learning, computer vision and natural language processing

I was a Program Commitee member of: 1st International Workshop on Big Data Analytic for Cyber Crime Investigation and Prevention

Teaching

Publications

2019   MANIS: Evading Malware Detection System on Graph Structure

The 35th ACM/SIGAPP Symposium On Applied Computing

2018   Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables

Proceedings of the European Signal Processing Conference (EUSIPCO 2018)

  Learning on a Budget for User Authentication on Mobile Devices

Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018)

2017   Spoilers: Effective Malware Triage Using Hidden Fields

Microsoft DCC

  Finding the Needle: A Study of the PE32 Rich Header and Respective Malware Triage

14th Conference on Detection of Intrusions and Malware & Vulnerability Assessment (DIMVA)

  Architecture for Resource-Aware VMI-based Cloud Malware Analysis

4th Workshop on Security in highly connected IT systems

  Empowering Convolutional Networks for Malware Classification and Analysis

30th International Joint Conference on Neural Networks (IJCNN)

2016   Deep Learning for Classification of Malware System Call Sequences

29th Australasian Joint Conference on Artificial Intelligence (AI)

  Adaptive Semantics-Aware Malware Classification

13th Conference on Detection of Intrusions and Malware \& Vulnerability Assessment (DIMVA)

2015   Neural Network-Based User-Independent Physical Activity Recognition for Mobile Devices

Intelligent Data Engineering and Automated Learning--IDEAL 2015

  CloudIDEA: A Malware Defense Architecture for Cloud Data Centers

5th International Symposium on Cloud Computing, Trusted Computing and Secure Virtual Infrastructures - Cloud and Trusted Computing (C&TC 2015)