Maksim E. Eren is an early career scientist in A-4, Los Alamos National Laboratory (LANL) Advanced Research in Cyber Systems division. He is an alumnus of the Scholarship for Service CyberCorps program. Maksim graduated Summa Cum Laude with a Bachelor’s degree in Computer Science from the University of Maryland Baltimore County (UMBC) in 2020 and earned his Master’s degree from the same institution in 2022. In 2024, he received his Ph.D. from UMBC, focusing on tensor decomposition methods for malware characterization.
Maksim’s interdisciplinary research interests lie at the intersection of machine learning and cybersecurity, with a focus on tensor decomposition. His tensor decomposition-based research projects encompass large-scale malware detection and characterization, cyber anomaly detection, data privacy, biology, text mining, large language models, knowledge graphs, and high-performance computing. Maksim has developed and published state-of-the-art solutions in anomaly detection and malware characterization. He has also worked on various other machine learning research projects, including detecting malicious hidden code, adversarial analysis of malware classifiers, and federated learning. At LANL, Maksim was a member of the 2021 R&D 100 winning project SmartTensors AI, where he has released a fast tensor decomposition and anomaly detection software, contributed to the design and development of various other tensor decomposition libraries, and developed state-of-the-art text mining tools.
PhD in Computer Science, 2024
University of Maryland, Baltimore County (UMBC)
MS in Computer Science, 2022
University of Maryland, Baltimore County (UMBC)
BS in Computer Science, 2020
University of Maryland, Baltimore County (UMBC)
AA in Computer Science, 2018
Montgomery College (MC)
Selected list of publications on tensor decomposition methods for cybersecurity and data privacy.
Using Anaconda and Jupyter for research has become a daily routine for me. Here I list some of the most frequent commands I utilize when setting up conda environments with Jupyter for my research proejcts.
Documenting your code is an important part of any project from developing a library to research code. In this blog post, I will give a brief tutorial on how to utilize Sphinx for documenting Python code. Sphinx is a tool utilized by several popular libraries. It turns the in-code comments into a user-friendly and modern documentation website.
Jupyter notebooks is a great way to work on research code. But notebooks used to analyse large datasets take long time to execute. And if our local or remote terminal session dies, our notebook dies too, resulting in waste of time. Here I summarize how we can run a notebook in headless mode in a screen session which allows us to run Jupyter notebook indipendent from the terminal session.
Tensor Extraction of Latent Features (T-ELF) is one of the machine learning software packages developed as part of the R&D 100 winning SmartTensors AI project at Los Alamos National Laboratory (LANL). T-ELF presents an array of customizable software solutions crafted for analysis of datasets.
pyCP_ALS is the Python implementation of CP-ALS algorithm that was originally introduced in the MATLAB Tensor Toolbox.
Random Forest of Tensors (RFoT) is a novel ensemble semi-supervised classification algorithm based on tensor decomposition. We show the capabilities of RFoT when classifying Windows Portable Executable (PE) malware and benign-ware.
pyDNTNK is a software package for applying non-negative Hierarchical Tensor decompositions such as Tensor train and Hierarchical Tucker decompositons in a distributed fashion to large datasets. It is built on top of pyDNMFk.
pyQBTNs is a Python library for boolean matrix and tensor factorization using D-Wave quantum annealers.
pyCP_APR is a Python library for tensor decomposition and anomaly detection that is developed as part of the R&D 100 award wining SmartTensors project. It is designed for the fast analysis of large datasets by accelerating computation speed using GPUs.
pyDNMFk is a software package for applying non-negative matrix factorization in a distributed fashion to large datasets. It has the ability to minimize the difference between reconstructed data and the original data through various norms (Frobenious, KL-divergence).
pyDRESCALk is a software package for applying non-negative RESCAL decomposition in a distributed fashion to large datasets. It can be utilized for decomposing relational datasets.