# Charles Grumer

> master of Computer Science & Engineering, University of Washington, 2019

**Wikidata**: [Q113667863](https://www.wikidata.org/wiki/Q113667863)  
**Source**: https://4ort.xyz/entity/charles-grumer

## Summary
Charles Grumer is a computer scientist who obtained a Master's degree in Computer Science & Engineering from the University of Washington in 2019. His academic work included a thesis focused on cybersecurity, specifically involving the hardening of Domain Generation Algorithm (DGA) classifiers using adversarial attacks and IVAP. He is recognized as a professional in the field of computer science, a discipline centered on the theoretical foundations of information and computation.

## Biography
*   **Education:** Master of Computer Science & Engineering, University of Washington (2019).
*   **Known for:** Research on adversarial attacks and DGA classifiers.
*   **Field(s):** Computer Science, Cybersecurity.
*   **Academic Advisor:** Martine De Cock.
*   **Occupation:** Computer Scientist.

## Contributions
Charles Grumer's primary known contribution is in the field of cybersecurity research, specifically through his academic thesis titled "Hardening Dga Classifiers Using Adversarial Attacks and Ivap." This work focuses on improving the robustness of classifiers designed to detect Domain Generation Algorithms (DGAs), which are often used by malware to evade detection. His research explores methods to defend these classifiers against adversarial attacks—techniques used to fool machine learning models—thereby strengthening security systems. This work was completed as part of his Master's degree at the University of Washington in 2019.

## FAQs
**Q: What is Charles Grumer known for?**
A: Charles Grumer is known for his 2019 Master's thesis, which researched methods to improve the security of DGA classifiers against adversarial attacks.

**Q: Where did Charles Grumer receive his education?**
A: He received his Master's degree in Computer Science & Engineering from the University of Washington in 2019.

**Q: What was the focus of Charles Grumer's research?**
A: His research focused on cybersecurity and machine learning, specifically on hardening classifiers that detect Domain Generation Algorithms (DGAs).

## Why They Matter
Charles Grumer's work contributes to the ongoing effort to secure digital infrastructure against evolving cyber threats. His research on hardening DGA classifiers addresses a critical vulnerability in network security: the ability of malware to communicate with command-and-control servers using randomly generated domain names. By exploring how to make these detection systems resistant to adversarial attacks, his work supports the development of more resilient and reliable security tools. This contribution is part of the broader computer science field's application of theoretical computation to solve practical, real-world problems in the industrial and service sectors.

## Notable For
*   **Academic Research:** Authoring the Master's thesis "Hardening Dga Classifiers Using Adversarial Attacks and Ivap."
*   **Cybersecurity Contribution:** Advancing techniques to protect machine learning models in security contexts from being fooled by adversarial examples.
*   **University of Washington Alumnus:** Successfully completing a graduate program at a major research university.

## Body
### Education and Academic Background
Charles Grumer pursued graduate studies in the field of computer science, a discipline defined by the study of theoretical foundations of information and computation. In 2019, he completed a Master of Computer Science & Engineering at the University of Washington. During his studies, he was a student of Martine De Cock, an academic associated with the university. His academic performance and research culminated in the completion of his degree, formally classifying him as a computer scientist.

### Research and Thesis
Grumer's academic contribution is encapsulated in his thesis, "Hardening Dga Classifiers Using Adversarial Attacks and Ivap." This work resides at the intersection of machine learning and cybersecurity. The research specifically addresses Domain Generation Algorithms (DGAs), which are used by botnets and malware to generate a large number of domain names to evade blacklisting. Grumer's thesis investigated methods to "harden" the classifiers used to detect these algorithmically generated domains. His approach involved using "adversarial attacks"—a technique where malicious inputs are crafted to confuse a model—to test and ultimately strengthen the classifier's resilience. This process of hardening helps ensure that security systems can more reliably distinguish between legitimate and malicious domains, even when faced with sophisticated evasion tactics.

## References

1. WorldCat