- 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
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
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)
