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.

Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

LASERBEAK: Evolving Website Fingerprinting Attacks with Attention and Multi-Channel Feature Representation

Published in IEEE Transactions on Information Forensics and Security (TIFS), 2024

This paper introduces LASERBEAK, a novel website fingerprinting attack that combines multi-channel feature representations and transformer-based attention mechanisms to significantly improve performance against defended Tor traffic.

Recommended citation: Nate Mathews, James K. Holland, Nicholas Hopper, Matthew Wright. (2024). "LASERBEAK: Evolving Website Fingerprinting Attacks with Attention and Multi-Channel Feature Representation." IEEE Transactions on Information Forensics and Security (TIFS), 2024. DOI: 10.1109/TIFS.2024.3468171.
Download Paper

Mockingbird: Defending Against Deep-Learning-Based Website Fingerprinting Attacks With Adversarial Traces

Published in IEEE Transactions on Information Forensics and Security (TIFS), 2020

This paper presents Mockingbird, a novel website fingerprinting defense that uses adversarial traces to significantly reduce the accuracy of deep-learning-based attacks while maintaining reasonable bandwidth overhead.

Recommended citation: Mohammad Saidur Rahman, Mohsen Imani, Nate Mathews, Matthew Wright. (2020). "Mockingbird: Defending Against Deep-Learning-Based Website Fingerprinting Attacks With Adversarial Traces." IEEE Transactions on Information Forensics and Security (TIFS), 2020. DOI: 10.1109/TIFS.2020.3039691.
Download Paper

Conference Papers

WhisperVoiceTrace: A Comprehensive Analysis of Voice Command Fingerprinting

Published in ACM Asia Conference on Computer and Communications Security (ASIA CCS), 2024

This paper presents WhisperVoiceTrace (WhiVo), a comprehensive analysis of voice command fingerprinting, proposing new features and methods for improved voice command traffic analysis in smart speakers like Amazon Alexa and Google Assistant.

Recommended citation: Minji Jo, Hyojin Kim, Jiwoo Hong, Hosung Kang, Nate Mathews, Se Eun Oh. (2024). "WhisperVoiceTrace: A Comprehensive Analysis of Voice Command Fingerprinting." ACM Asia Conference on Computer and Communications Security (ASIA CCS), 2024. DOI: 10.1145/3634737.3657017.
Download Paper

SoK: A Critical Evaluation of Efficient Website Fingerprinting Defenses

Published in IEEE Symposium on Security and Privacy (SP), 2023

This paper provides a critical evaluation of nine recent efficient website fingerprinting defenses, utilizing deep-learning-based attacks and considering their real-world deployability in Tor.

Recommended citation: Nate Mathews, James K. Holland, Se Eun Oh, Mohammad Saidur Rahman, Nicholas Hopper, Matthew Wright. (2023). "SoK: A Critical Evaluation of Efficient Website Fingerprinting Defenses." IEEE Symposium on Security and Privacy (SP), 2023. DOI: 10.1109/SP46215.2023.10179289.
Download Paper | Download Slides

DeepCoFFEA: Improved Flow Correlation Attacks on Tor via Metric Learning and Amplification

Published in IEEE Symposium on Security and Privacy (SP), 2022

This paper presents DeepCoFFEA, a novel end-to-end flow correlation attack that significantly improves the accuracy of flow correlation on the Tor network by using deep metric learning and amplification techniques.

Recommended citation: Se Eun Oh, Taiji Yang, Nate Mathews, James K. Holland, Mohammad Saidur Rahman, Nicholas Hopper, Matthew Wright. (2022). "DeepCoFFEA: Improved Flow Correlation Attacks on Tor via Metric Learning and Amplification." IEEE Symposium on Security and Privacy (SP), 2022. DOI: 10.1109/SP46214.2022.9833801.
Download Paper

What a SHAME: Smart Assistant Voice Command Fingerprinting Utilizing Deep Learning

Published in 20th Workshop on Privacy in the Electronic Society (WPES), 2021

This paper introduces SHAME, a deep learning-based voice command fingerprinting attack model that leverages packet metadata to infer voice commands issued to smart assistants like Amazon Echo and Google Home.

Recommended citation: Jack Hyland, Conrad Schneggenburger, Nick Lim, Jake Ruud, Nate Mathews, Matthew Wright. (2021). "What a SHAME: Smart Assistant Voice Command Fingerprinting Utilizing Deep Learning." 20th Workshop on Privacy in the Electronic Society (WPES), 2021. DOI: 10.1145/3463676.3485615.
Download Paper | Download Slides

GANDaLF: GAN for Data-Limited Fingerprinting

Published in Proceedings on Privacy Enhancing Technologies (PoPETS), 2021

This paper introduces GANDaLF, a novel deep-learning-based Website Fingerprinting (WF) attack using Generative Adversarial Networks (GANs) designed to work effectively with limited training data.

Recommended citation: Se Eun Oh, Nate Mathews, Mohammad Saidur Rahman, Matthew Wright, Nicholas Hopper. (2021). "GANDaLF: GAN for Data-Limited Fingerprinting." Proceedings on Privacy Enhancing Technologies (PoPETS), 2021. DOI: 10.2478/popets-2021-0029.
Download Paper | Download Slides

Tik-Tok: The Utility of Packet Timing in Website Fingerprinting Attacks

Published in Proceedings on Privacy Enhancing Technologies (PoPETS), 2020

This paper explores the use of packet timing in website fingerprinting (WF) attacks, showing that timing information significantly improves the accuracy of WF classifiers in both closed-world and open-world settings.

Recommended citation: Mohammad Saidur Rahman, Payap Sirinam, Nate Mathews, Kantha Girish Gangadhara, Matthew Wright. (2020). "Tik-Tok: The Utility of Packet Timing in Website Fingerprinting Attacks." Proceedings on Privacy Enhancing Technologies (PoPETS), 2020. DOI: 10.2478/popets-2020-0043.
Download Paper

Triplet Fingerprinting: More Practical and Portable Website Fingerprinting with N-shot Learning

Published in ACM SIGSAC Conference on Computer and Communications Security (CCS), 2019

This paper introduces Triplet Fingerprinting (TF), a novel website fingerprinting attack that uses N-shot learning to reduce training data requirements while remaining effective under varying network conditions.

Recommended citation: Payap Sirinam, Nate Mathews, Mohammad Saidur Rahman, Matthew Wright. (2019). "Triplet Fingerprinting: More Practical and Portable Website Fingerprinting with N-shot Learning." ACM SIGSAC Conference on Computer and Communications Security (CCS), 2019. DOI: 10.1145/3319535.3354217.
Download Paper | Download Slides

Understanding Feature Discovery in Website Fingerprinting Attacks

Published in IEEE Western New York Image and Signal Processing Workshop (WNYISPW), 2018

This paper explores how convolutional neural networks discover and exploit features in website fingerprinting attacks on the Tor network.

Recommended citation: Nate Mathews, Payap Sirinam, Matthew Wright. (2018). "Understanding Feature Discovery in Website Fingerprinting Attacks." IEEE Western New York Image and Signal Processing Workshop (WNYISPW), 2018. DOI: 10.1109/WNYIPW.2018.8576379.
Download Paper | Download Slides