Nate Mathews

Nate Mathews

PhD Candidate specializing in the application of machine learning and deep learning techniques to address cybersecurity challenges, particularly in network traffic analysis.

Talks and presentations

Teaching Generative AI for Cybersecurity: A Project-Based Learning Approach

November 27, 2024

Talk, 28th Colloquium for Information Systems Security Education (CISSE), Tampa, Florida

At the 28th Colloquium for Information Systems Security Education (CISSE), I presented our work on teaching Generative AI for cybersecurity through a hands-on, project-based learning approach. The course explores the application of large language models (LLMs) to automate cybersecurity tasks, emphasizing real-world case studies, prompt engineering, fine-tuning, and retrieval-augmented generation (RAG).

Colloquium Talk: Harnessing AI for Advanced Network Security

October 11, 2024

Talk, Washington University in St. Louis (WashU), St. Louis, Missouri

This is a repeat of the same talk presented a few days prior at Rochester Security Summit, with modifications for an academic crowd as part of WashU’s graduate colloquium series.

Harnessing AI for Advanced Network Security: From Attacks on Privacy to Defensive Innovations

October 09, 2024

Talk, Rochester Security Summit (RSS), Rochester, New York

In this talk, myself and my advisor, Dr. Matthew Wright, explored the AI techniques we used to develop a novel stepping-stone identification method. A key focus was on Flow Correlation attacks, a class of attacks that target anonymity networks but can be adapted to defense, particularly for detecting pivoting in network intrusion attacks.

Critical Evaluation of Efficient Website Fingerprinting Defenses

May 01, 2023

Talk, IEEE Symposium on Security and Privacy (S&P), San Francisco, California

Presented research on the paper “SoK: A Critical Evaluation of Efficient Website Fingerprinting Defenses” at the IEEE S&P 2023. This talk covered the comprehensive evaluation of nine recent defenses and their performance against deep-learning-based website fingerprinting attacks.

GANDaLF: GAN for Data-Limited Fingerprinting

July 12, 2021

Talk, Privacy Enhancing Technologies Symposium (PETS), Virtual Event

Presented research on “GANDaLF: GAN for Data-Limited Fingerprinting” at PETS 2021. This talk highlighted the novel use of Generative Adversarial Networks (GANs) to improve website fingerprinting attacks in data-limited scenarios, outperforming existing methods in subpage fingerprinting.

Deanonymizing Internet Traffic with Website Fingerprinting

July 27, 2020

Talk, IETF-108, PEARG, Virtual Event

Gave an invited talk on the topic of “Deanonymizing Internet Traffic with Website Fingerprinting” for the Privacy Enhancements and Assessments Research Group (PEARG) at IETF-108. This presentation discussed new techniques and research directions for analyzing traffic and compromising privacy in encrypted network environments.

Triplet Fingerprinting: N-shot Learning for Website Fingerprinting

November 11, 2019

Talk, ACM Conference on Computer and Communications Security (CCS), London, UK

Presented research on “Triplet Fingerprinting: More Practical and Portable Website Fingerprinting with N-shot Learning” at ACM CCS 2019. The talk introduced the novel triplet learning-based approach to website fingerprinting, significantly reducing the data requirements while maintaining effectiveness across different network conditions.