Caglar Oksuz

Welcome to my personal academic webpage!

I am a Ph.D. candidate in Computer Science at Case Western Reserve University, with a strong focus on machine learning security, privacy, and adversarial robustness. My research centers around black-box threats against machine learning models such as model extraction and label-only membership inference attacks, particularly under realistic, resource-constrained scenarios. I also explore how explainable AI (XAI) techniques can inadvertently leak sensitive model information, and how such vulnerabilities can be exploited and mitigated.

I develop attack frameworks and privacy-preserving mechanisms across various domains including genomic data, web platforms, and ML-as-a-Service environments. I actively build tools and conduct evaluations that push the boundaries of adversarial machine learning research while maintaining a strong interest in policy, ethics, and law through my parallel legal education.

My work focuses on:

Privacy
Computer Security
Explainable AI (XAI)
Adversarial Machine Learning

🎓 Education

Ph.D. in Computer Science @ Case Western Reserve University (Present)

LL.B. in Law @ Ankara University (Present)

M.S. in Computer Science @ Bilkent University (August 2020)

B.S. in Computer Science @ Bilkent University (June 2017) (Minor in Psychology)

Erasmus+ Exchange Student @ Roskilde University (June 2015)

💼 Experience

Graduate Researcher @ Case Western Reserve University (Aug 2021 – present)

Assisted courses of Data Structures, and Data Privacy by grading and tutoring.
Built a novel model extraction attack framework leveraging Explainable AI (XAI) tools LIME and SHAP to replicate black-box models from MLaaS platforms (Google Cloud, IBM Watson). Reduced query overhead by up to 240x on select datasets. Utilized Python, scikit-learn, NumPy, Pandas, Git, and containerized deployment via Docker. GitHub Repo
Implemented a query-efficient, label-only membership inference framework on neural networks using active-learning and transfer-learning-based model extraction. Performed hyperparameter optimization via grid search, integrated privacy defenses (DP-SGD, adversarial training, L2 regularization), and managed model training workflows with PyTorch.

Graduate Researcher @ Bilkent University (Sep 2017 – Aug 2020)

Assisted courses of Introduction to Programming I & II, and Artificial Intelligence by grading and tutoring.
Developed a privacy-preserving watermarking scheme for genomic data, using local differential privacy (LDP) in MATLAB. Achieved up to 80% detection rate with under 5% utility loss against collusion attacks. GitHub Repo

Software Engineering Intern @ ASELSAN (Jul 2015 – Aug 2015)

Engineered and deployed a highly responsive user interface and control panel for military hardware. Utilized ASP.NET MVC 5 for robust back-end functionality and integrated HTML5, CSS3, and C# for a dynamic front-end design. This system was adopted as an official prototype.

Software Engineering Intern @ Nokta Medya (Aug 2014- Sep 2014)

Developed an automated content moderation algorithm to speed up content moderation, reduced response time by 21%, and improved platform compliance using Python and data-driven insights.
Tracked, analyzed, and reported daily website analytics using Google Analytics, Microsoft Excel and SQL, identifying trends that increased user engagement by 16% and retention by 12% over six months.
Assisted business intelligence team to lead a search engine optimization (SEO) workshop for the management and product teams. Implemented strategies that improved organic search visibility by 26%, boosting site traffic.
Conducted comparative analysis between the product features of video sharing platforms izlesene.com, YouTube, Dailymotion and Vimeo. Delivered a presentation to department heads and the CEO key opportunities that resulted in the adoption of 3 key product features and increasing the adaptability of the product by 30%.

🔬 Publications

Find my latest research on: Google Scholar

AUTOLYCUS: Exploiting Explainable Artificial Intelligence (XAI) for Model Extraction Attacks against Interpretable Models

This study proposes a model extraction attack that leverages explainable AI (XAI) techniques to compromise and steal interpretable models. (GitHub Repo) (doi)

Privacy-preserving and robust watermarking on sequential genome data using belief propagation and local differential privacy

This study proposes a robust and privacy-preserving genomic watermarking scheme that embeds identifiable markers into sequential genome data using belief propagation and local differential privacy to resist collusion and inference attacks. (GitHub Repo) (doi)

🔍 Projects

Follower Analyzer

A graph-based data analyzer on Matlab to extract, evaluate and visualize follower interactions on Instagram. Utilized for keeping track of followers, follower interactions, and notify users for followers who quit following.

Family Linker

A Python application that automates web scraping and ETL pipelines to extract structured social and familial relationship data of Northeast Ohio residents from voter registration and people finding web sites. Utilized Jupyter, and libraries BeautifulSoup, selenium, chromium, pandas and numpy to automate linkage and analysis. (GitHub Repo)

Spoiler Blocker

A Chrome extension designed to block spoiler content annotated by users on websites. Developed using React, Django, MySQL, and JavaScript, deployed via Google Cloud, with version control managed through Git. (GitHub Repo)

📬 Contact

If you’d like to collaborate or have any questions, feel free to reach out:

📧 Email: acoksuz0@gmail.com
🌐 Website: acoksuz.github.io
💼 LinkedIn: https://www.linkedin.com/in/acoksuz/
🧑‍💻 GitHub: https://github.com/acoksuz/