Brad Miller

I am a software engineer at Google, where I am a tech lead on the Safe Browsing team. My work focuses is on detecting malicious websites distributing phishing and malware. I also have a PhD in Computer Science from UC Berkeley, where I was advised by Anthony D. Joseph and Doug Tygar and collaborated occasionally with Vern Paxson. Before that I did a bachelors in Electrical and Computer Engineering at Carnegie Mellon, where I was advised by Lujo Bauer. My research and current work focus on security applications of machine learning.

Email: Click me to reveal email.

Publications

PREDATOR: Proactive Recognition and Elimination of Domain Abuse at Time-Of-Registration
S. Hao, A. Kantchelian, B. Miller, N. Feamster, V. Paxson.
23rd ACM Conference on Computer and Communications Security (CCS), October 2016.

Press Coverage

Wall Street Journal: Algorithm Red Flags Potentially Dangerous Domain Names at Time of Purchase
Daily Mail: Say goodbye to internet scams: New system catches out malicious websites before they are even registered
CircleID: New Technique Detects and Eliminates Abusive Domains at Time of Registration

Reviewer Integration and Performance Measurement for Malware Detection
B. Miller, A. Kantchelian, S. Afroz, R. Bachwani, R. Faizullabhoy, L. Huang, V. Shankar, M.C. Tschantz, T. Wu, G. Yiu, A.D. Joseph, J.D. Tygar.
16th Conference on Detection of Intrusions, Malware & Vulnerability Assessment (DIMVA), July 2016.

Resources

Further resources in relation to this project, including code and data, are available at the project homepage.

Better Malware Ground Truth: Techniques for Weighting Anti-Virus Vendors Labels
A. Kantchelian, M.C. Tschantz, S. Afroz, B. Miller, V. Shankar, R. Bachwani, A.D. Joseph, J.D. Tygar.
8th ACM Workshop on Artificial Intelligence and Security (AISec), October 2015.

Adversarial Active Learning
B. Miller, A. Kantchelian, S. Afroz, R. Bachwani, E. Dauber, L. Huang, M.C. Tschantz, A.D. Joseph, J.D. Tygar.
7th ACM Workshop on Artificial Intelligence and Security (AISec), November 2014.

I Know Why You Went to the Clinic: Risks and Realization of HTTPS Traffic Analysis
B. Miller, L. Huang, A.D. Joseph and J.D. Tygar.
14th Privacy Enhancing Technologies Symposium (PETS), July 2014. Winner of Best Student Paper Award.

Press Coverage Resources

Wall Street Journal: Researchers use big data to get around encryption
MIT Technology Review: Statistical tricks extract sensitive data from encrypted communications
PC World: Even encrypted Web traffic can reveal highly sensitive information
Ars Technica: New attack on HTTPS crypto might reveal if you're pregnant or have cancer
Threatpost: New attacks on HTTPS traffic reveal plenty about your web surving
CSO Online: Researchers attack secured Internet activity to mine personal data

Further resources in relation to this project, including code and data, are available at the project homepage.

Approaches to Adversarial Drift
A. Kantchelian, S. Afroz, L. Huang, A. Islam, B. Miller, M. Tschantz, R. Greenstadt, A.D. Joseph and J.D. Tygar.
6th ACM Workshop on Artificial Intelligence and Security (AISec), November 2013.

Systematic Analysis and Evaluation of Web Privacy Policies and Implementations
B. Miller, K. Buck and J.D. Tygar.
7th International Conference for Internet Technology and Secure Transactions (ICITST), December 2012.

What's Clicking What? Techniques and Innovations of Today's Clickbots
B. Miller, P. Pearce, C. Grier, C. Kreibich and V. Paxson.
11th Conference on Detection of Intrusions, Malware & Vulnerability Assessment (DIMVA), July 2011.

Theses

Scalable Platform for Malicious Content Detection Integrating Machine Learning and Manual Review
PhD Thesis, UC Berkeley.
Filed August 2015.
Advisors: Anthony D. Joseph and J.D. Tygar.

HTTPS Vulnerability to Fine Grain Traffic Analysis
MS Thesis, UC Berkeley.
Filed December 2012.
Advisor: J.D. Tygar.

Invited Talks

Panelist: AI for cybersecurity: what are the next revolutions, and where will they stop?
CyberSec&AI
Virtual Event, November 2021.

Improving Binary Classifiers Through Evaluation and Labeling
King's College London.
London, January 2020.

Malicious Content Detection with Temporal Consistency and Manual Review
LinkedIn.
Mountain View, June 2015.

Do Try This at Home: Autograders for an AI Course
Berkeley Institute of Design (BiD) Seminar.
Berkeley, October 2013.

Guest Lecture for 18-200 Emerging Trends in Electrical and Computer Engineering
Carnegie Mellon University.
Pittsburgh, September 2012.

What's Clicking What? Techniques and Innovations of Today's Clickbots
Google Inc.
Mountain View, March 2011.

Teaching

Computer Security
Graduate Student Instructor / Teaching Assistant
UC Berkeley, Fall 2013.

Introduction to Artificial Intelligence
Graduate Student Instructor / Teaching Assistant
UC Berkeley & edX.org, Spring 2013.

More Info

This course was simultaneously offered on UC Berkely's campus and on edX.org. My primary contribution was the development of a new auto-grading system for the Pac-Man Projects. The autograding system improved the projects by allowing students to grade their code locally and providing detailed, transparent test cases. The autograder has since beed used by hundreds of students at UC Berkeley and thousands of students on edX.org and at other institutions.

Professional Service

Artifact Evaluation Committee for USENIX Security Symposium (2022)

Program Committee for USENIX Security Symposium (2021)

Program Committee for ACM Workshop on Artificial Intelligence and Security (2016-2021; 2017 PC Co-Chair)

Reviewer for International Journal of Information Security (IJIS)

Reviewer for IEEE Transactions on Information Forensics & Security (IEEE T-IFS)