- 👋 I am a Graduate Research Assistant at ISML Lab, Gachon University, and doing my Masters degree in Computer Engineering at Gachon University.
- 🔭 My area of research is federated learning, and my research topic is detection of poisoning attacks in federated learning.
- 👀 I've been interested in programming since the very first time I took C++ course in my undergraduate degree.
- After that, I have written codes in other programming languages at some basic level, such as JavaScript, MATLAB, and C.
- Now, I mostly code in Python because it is more suitable for research and development in AI, machine learning, and deep learning.
-
Graduate Research Assistant | March 2022 - Present | Information Security & Machine Learning Lab, Gachon University, South Korea
-
Research on Federated Learning
- Developed a federated learning framework using Python, PyTorch, and threading
- Implemented and evaluated the performance of various deep learning models e.g., AlexNet, VGG16, and ResNet18 within my federated learning codebase
- Implemented and analyzed the impact of poisoning attacks on the performance of federated learning
- Integrated state-of-the-art poisoning attack defense methods into the codebase for benchmarking purposes
- Proposed a novel defense method that outperformed the state-of-the-art in terms of poisoning attack detection accuracy
- Authored a research article currently under review in an IEEE journal
- Currently surveying defense methods against poisoning attacks in asynchronous federated learning
-
Research on Tracing Attackers Over Overlay Networks
- Conducted a thorough survey on deanonymization attacks targeting the Tor overlay network, with a specific focus on deep learning-based correlation attacks
- Performed an in-depth analysis of the prominent deep learning-based correlation attack, DeepCoFFEA identifying critical issues such as high memory consumption and correlation time
- Successfully mitigated memory-related challenges, reducing consumption from 133GB to 70GB through effective memory deallocation and proactive garbage collection strategies
- Achieved a seven times reduction in correlation time by leveraging GPU processing, facilitated by PyCUDA library.
- Published a research article in IEEE Access journal, outlining the findings and implemented solutions
-
-
Intern | February 2021 - April 2021 | National Center of Artificial Intelligence at UET Peshawar, Pakistan
- Contributed to the Landslide Monitoring and Alert System Project
- Collected landslide videos to form a dataset for input into deep learning models
- Segmented and annotated videos into pre-landslide, landslide, and post-landslide phases by utilizing a custom Python script
-
Languages 👉 Python | C/C++ | JavaScript
-
ML/DL Frameworks 👉 PyTorch | Keras | TensorFlow | scikit-learn
-
Python Libraries 👉 NumPy | OpenCV | Matplotlib | Pandas | scikit-image | Tkinter | sqlite3 | PyCUDA | threading
-
Development Tools 👉 Visual Studio Code | Jupyter Notebook | Git | GitHub | Docker
-
Operating Systems 👉 Ubuntu | Windows
-
Soft Skills 👉 Communication | Teamwork | Problem-Solving | Critical Thinking
- M. A. Hafeez, Y. Ali, K. H. Han and S. O. Hwang, "GPU-Accelerated Deep Learning-Based Correlation Attack on Tor Networks," in IEEE Access, vol. 11, pp. 124139-124149, 2023, doi:10.1109/ACCESS.2023.3330208. (Impact Factor: 3.9)
- Code is available here.
- Y. Ali, K. H. Han, et al. "An Optimal Two-Step Approach for Defense Against Poisoning Attacks in Federated Learning" (under review)
- Let's connect on Linkedin: LinkedIn
- You can reach out to me at [email protected]