Skip to content
View krassiaa's full-sized avatar

Block or report krassiaa

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
krassiaa/README.md

banner

ML engineer

  • Studying Software Engineering at CSU
  • Worked on Telegram bots and developed a projects using Python
  • Developed a web service using Python that I really enjoy!
  • How to reach me: skid.series.9y@icloud.com
  • My Linkedin

Tech Stack

💼 Commercial Experience

deepfake-detection — R&D project for industrial deepfake detection on edge devices.

  • Developed a lightweight detection pipeline using MobileNetV4 (9.2M params)
  • Achieved 99.6% ROC-AUC, comparable to heavy DINOv2 (22.1M params)
  • Built custom dataset AuthorDeepFake-6600 with InSwapper & SDXL generations
  • Deployed on NVIDIA RTX 3090 for training, targeting mobile/edge inference

🎓 Academic Research

adversarial_pipeline — Master's thesis on real-time adversarial attacks against face recognition.

  • Adapted NI-FGSM for video streams (33.6 FPS on Apple M1 Pro)
  • Achieved 99.75% ASR with imperceptible perturbations (PSNR > 36 dB)

GitHub last commit

@krassiaa's activity is private