About
Education
Research
Projects
Skills
Coursework
Contact
Download CV (PDF)Bekhzod_CV_Cybersecurity_Analyst_EN.pdf
Copy email addressvirtsudo@proton.me
Send an emailvirtsudo@proton.me
Open GitHubgithub.com/virtsudo
Open LinkedInlinkedin.com/in/virtsudo
Software Engineer
Machine Learning Engineer
ItalianoSwitch to Italian
Light theme
Dark theme
System theme

Open to junior roles and internships in cybersecurity, on-site or remote.

BekhzodAnvarov.

Cybersecurity AnalystNetwork Intrusion Detection · Network Traffic Analysis · Anomaly Detection

  • Wireshark
  • Nmap
  • Burp Suite

whoami

Bekhzod Anvarov

cat role.txt

Cybersecurity Analyst

cat focus.txt

Network Intrusion Detection

Network Traffic Analysis

Anomaly Detection

cat location.txt

Turin, Italy

// about me

About

Computer Engineering graduate (MSc, Cybersecurity track) from Politecnico di Torino, focused on network intrusion detection.

For my thesis I built an intrusion detection pipeline and tested it on real backbone traffic from 2011, 2016 and 2021. Open to junior roles and internships in cybersecurity, on-site or remote.

// background

Education

  1. Master of Science in Computer Engineering (Cybersecurity track)

    Politecnico di Torino

    2026

  2. Bachelor’s Degree in Computer Engineering

    Politecnico di Torino

    2022

// research

Research experience

Master’s thesis · Politecnico di Torino · 2026

JEPA Representation Learning for Intrusion Detection on Real-World Drifting Network Traffic

Supervisors: Prof. Guido Marchetto, Prof. Alessio Sacco, Cristiano Serra, MSc

Does a representation learned from unlabeled network traffic keep an intrusion classifier more accurate than raw flow features on traffic recorded years later?
  1. Built an intrusion detection pipeline in Python with flow preprocessing, a self-supervised JEPA model in PyTorch and four classifiers (logistic regression, decision tree, random forest, XGBoost), using real Internet backbone traffic from 2011, 2016 and 2021 (MAWIFlow benchmark with CICFlowMeter flow features and MAWILab labels).

  2. Tested each year’s classifiers on every year. The representation made anomalous traffic easier to separate with a linear model but did not reduce the drop across years, and the labels changed meaning after 2011.

  3. Audited the benchmark. Showed that its scaling lost most of the resolution in the flow features and replaced it, and found that its published metrics contradict its published samples for two of the three years.

  • Python
  • PyTorch (CUDA)
  • scikit-learn
  • XGBoost
  • Polars
  • NumPy
  • Matplotlib

// featured work

Projects

Built an FFNN for network intrusion detection and FFNN, RNN and GNN models for malware classification. Fine-tuned BERT to analyze SSH logs and tag them with MITRE ATT&CK tactics.

  • Python
  • PyTorch
  • Jupyter
  • Hugging Face

// capabilities

Skills

Security tools (coursework)

  • Wireshark
  • Nmap
  • Burp Suite

Programming & tools

  • Python
  • C/C++
  • SQL (MySQL, SQLite)
  • Linux shell
  • Git/GitLab

Machine learning

  • PyTorch
  • scikit-learn
  • XGBoost
  • Hugging Face

Languages

  • UzbekNative
  • RussianC1
  • EnglishB2
  • ItalianB1

// at university

Relevant coursework

  • Security Verification and Testing

    vulnerability assessment, penetration testing, static code analysis.

  • Information Systems Security

    attacks and risk analysis, PKI, IPsec, TLS, SSH, firewalls and IDS, VPNs.

  • Cybersecurity

    federated authentication (SAML, OIDC), Trusted Execution Environments, forensic analysis.

  • Data Protection, Privacy and Anonymity

    identity and access management, anonymization, re-identification.

  • AI and Cybersecurity

    deep learning, anomaly detection, traffic classification.

  • Cryptography

    AES, RSA, SHA-3, digital signatures, ECDH, cryptographic programming in C and Python.

  • Computer Network Technologies and Services

    IPv4/IPv6 network design, Internet routing, VPNs, MPLS.

// get in touch

Contact

Turin, Italy