Avatar

Brandon Paulsen

PhD Student in Computer Science

University of Southern California

Biography

Hello! I’m Brandon, and I’m a PhD student in Computer Science at the University of Southern California advised by Professor Chao Wang. My research interests broadly lie in applying program analysis and verification techniques to security and reliability related problems. Most recently, I’ve focused on side channel mitigation and verifying properties of machine learning models. Before joining USC I received a Master’s degree in CS from the University of Minnesota, Duluth advised by Professor Peter A.H. Peterson, and I was also previously a visiting research assistant at USC’s ISI under the supervision of Jelena Mirkovic.

Outside of research, I stay active through rock climbing and weight lifting. 还有因为很多我的朋友们是中国人,所以我在空闲时间喜欢学习汉语。

Interests

  • Security and Reliability
  • Side Channel Detection and Mitigation
  • Verification of Machine Learning Models

Education

  • PhD in Computer Science, 2022

    University of Southern California

  • M.S. in Computer Science, 2017

    University of Minnesota, Duluth

  • B.Sc. in Computer Science, 2015

    University of Minnesota, Duluth

Publications

NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation.
Brandon Paulsen, Jingbo Wang, Jiawei Wang, and Chao Wang.
35th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2020.
(PDF)

ReluDiff: Differential Verification of Deep Neural Networks.
Brandon Paulsen, Jingbo Wang, and Chao Wang.
42nd IEEE/ACM International Conference on Software Engineering (ICSE), 2020.
(PDF) (Artifact)

Debreach: Mitigating Compression Side Channels via Static Analysis and Transformation.
Brandon Paulsen, Chungha Sung, Peter Peterson, and Chao Wang.
34th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2019.
(PDF) (Artifact)

CANAL: A Cache Timing Analysis Framework via LLVM Transformation.
Chungha Sung, Brandon Paulsen, Chao Wang.
33rd IEEE/ACM International Conference on Automated Software Engineering (ASE) Tool Demo Track, 2018.
(PDF) (Artifact)

Debreach: Selective Dictionary Compression to Prevent BREACH and CRIME.
Brandon Paulsen, Peter A.H. Peterson.
Masters thesis.
(PDF) (Compressor artifact located in ASE 2019 artifact)

A Comparison of Sorting Times between Java 8 and Parallel Colt: an Exploratory Experiment.
Andrew Brooks, Laura Krebs, and Brandon Paulsen.
SIGSOFT Software Engineering Notes 41, 2016.
(PDF)

Beta-testing a requirements analysis tool.
Andrew Brooks, Laura Krebs, and Brandon Paulsen.
SIGSOFT Software Engineering Notes 39, 2014.
(PDF)

Experience

 
 
 
 
 

Research Assistant

USC

August 2017 – Present California

Researched several topics including:

  • AI Safety, Neural Network Verification
  • Mitigating side channel attacks
 
 
 
 
 

Visiting Research Assistant

USC

May 2016 – August 2016 California
Worked on the project Flash cRowd Attack DEfense (FRADE) to research defenses against application-level distributed denial of service attacks
 
 
 
 
 

Research Assistant

Univ. of Minnesota, Duluth

August 2015 – August 2017 Minnesota

Projects included:

  • Researching defenses against compression side channel attacks (see my master’s thesis)
  • Building a network testbed based on the DETER project

Contact