visal@sec:~$
Cybersecurity · Machine learning · Peshawar, PK

Visal Sattar Breaks his own tools

I'm a computer science graduate who builds network security tools and then tests where they fail. I'm looking for an entry-level security role and working toward offensive security and AI red teaming.

BS Computer Science, 2026Google Cybersecurity CertificateSecurity+ in progress
bash · type help
Final-year project · Jan 2025 to May 2026

AI-based intrusion detection

A real-time pipeline that captures live traffic, scores each flow with machine-learning models trained on CICIDS2017, and pushes enriched alerts to a dashboard. I led the engineering on a three-person team. Run either test below to see what happened.

CaptureScapy + Npcap on the Windows host
Features78 CICFlowMeter flow features
Random Forestknown attack patterns
Autoencoderanomaly score
Rate ruleconnections per second
DashboardRedis Streams, Socket.IO, GeoIP, AbuseIPDB
// pick a test above

99.50%

Random Forest F1 on a held-out CICIDS2017 split of 45,149 flows. DDoS traffic only.

99.4%

Replay recall at 100% precision, up from 52% after I found and fixed three mismatches in my feature extractor.

<1 s

Rate rule I added after the models missed a real flood from my phone.

222

pytest tests covering preprocessing, train/test leakage, fusion logic, route security and blocking.

Known limitsLatency is measured only from Redis to the dashboard (2.5 ms median), not end to end from capture to browser. The models only recognise attack types they were trained on; that's why the rate rule exists. By design, unconfirmed anomaly alerts are capped at MEDIUM so a guess can never trigger blocking.
PythonScapyscikit-learnTensorFlowFlaskRedis StreamsReactDocker Compose
Other work

Projects

Personal project · Feb to Dec 2024

Underwater trash detection

I fine-tuned a YOLOv8s segmentation model on the TrashCan underwater dataset and served it through a Flask app with filename sanitising and a file-type allowlist. It reached 0.712 box mAP@50 after a 10-epoch baseline run.

Python · YOLOv8 · PyTorch · OpenCV · Flask
Read the code ↗
Internship · Jun to Dec 2023

Bureau of Agriculture Information KP

As a web development and database intern I built responsive intranet pages, designed the SQL schemas behind the department's internal reports, and wrote a JavaScript time-tracking tool staff used.

HTML · CSS · JavaScript · Bootstrap · SQL
Lab notes

Writeups

Walkthroughs of the labs I solve, with what I tried, what failed and how I got in.

Coming soon

PortSwigger Web Security Academy

Writeups of the PortSwigger labs I solve: what I tried, what failed, and what got me in. The first ones go up in November 2026.

Coming soon

TryHackMe rooms

Notes from the rooms I complete alongside the PortSwigger labs.

Where I'm headed

The path

My plan from here to an offensive security role.

  1. FoundationsCS degree, IDS project, Google Cybersecurity Certificate
  2. Web hackingSecurity+ course and PortSwigger labs
  3. CertificationsCompTIA Security+ in early 2027, then BSCP
  4. AI red teamingAttacking machine-learning and LLM systems
  5. Real-world proofActive Directory, public findings, writeups

Education

  • BS Computer ScienceThe University of Agriculture, Peshawar · 2022 to 2026

Certifications

  • Google Cybersecurity Professional CertificateCompleted May 2026
  • CompTIA Security+In progress, exam planned for early 2027

Tools

  • Security and networkingScapy, Npcap, traffic analysis, TCP/IP, Linux, PowerShell
  • BuildingPython, Docker, Flask, Redis, React, Git
Get in touch

Contact

Based in Peshawar. Open to entry-level security and IT roles: on-site in Pakistan, remote, or relocating abroad. Found the flag? Email it to me.