William Frederick Koch III

wfkoch at gmail dot com

Bio

Wil Koch received his BS in computer engineering from University of Rhode Island where he developed interests in machine learning and cyber security. After graduation he worked as a software engineer for six years on the Sikorsky CH-53K King Stallion helicopter project before returning back to academia to receive his MS in machine learning from Stevens Institute of Technology. To focus on his growing interest in cyber security he came to Boston University for his PhD where he was advised by Azer Bestavros. He has published a number of papers in a wide area of cyber security including static and dynamic malware analysis, vulnerability analysis, cyber defense and attacks, and mobile security.

In 2017, Wil was introduced to first-person-view (FPV) drone racing and was immediately drawn to the sport for his love of flight, racing and engineering. This passion drove a shift in his research. He began working with Renato Mancuso, Richard West, and Azer Bestavros to fuse together machine learning and flight control leading to the development of the world's first neural network supported flight control firmware, Neuroflight. In the summer of 2019, Wil received his PhD from Boston University. His thesis, "Flight Controller Synthesis via Deep Reinforcement Learning" has established a baseline for developing next generation flight control systems, opening up new opportunities for advanced aircraft design.

As a leader and someone who encourages continued learning Wil has co-founded CT Hackerspace, Connecticut's oldest and largest hackerspace and founded Boston Drone Racing, an FPV drone racing and hacking club.


Projects

Neuroflight

Neuroflight is the first open source neuro-flight controller software (firmware) for remotely piloting multi-rotors and fixed wing aircraft. Neuroflight's primary focus is to provide optimal flight performance.

View Project

GymFC

GymFC is an OpenAI Gym environment designed for synthesizing intelligent flight control systems using reinforcement learning. This environment is meant to serve as a tool for researchers to benchmark their controllers to progress the state-of-the art of intelligent flight control.

View Project

Selected Publications

Neuroflight: Next Generation Flight Control Firmware

William Koch, Renato Mancuso, Azer Bestavros

Pre-print PDF

January 2019

Reinforcement Learning for UAV Attitude Control

William Koch, Renato Mancuso, Richard West, Azer Bestavros

ACM Transactions on Cyber-Physical Systems PDF

January 2019

Identifier Binding Attacks and Defenses in Software-Defined Networks

Samuel Jero, William Koch, Rickard Skowyra, Hamed Okhravi, Cristina Nita-Rotaru, David Bigelow

USENIX Security Symposium PDF

August 2017

Semi-Automated Discovery of Server-Based Information Oversharing Vulnerabilities in Android Applications

William Koch, Abdelberi Chaabane, Manuel Egele, William Robertson, Engin Kirda

ACM International Symposium on Software Testing and Analysis (ISSTA) PDF

July 2017

PayBreak: Defense Against Cryptographic Ransomware

Eugene Kolodenker, William Koch, Gianluca Stringhini, Manuel Egele

ACM Asia Conference on Computer and Communications Security (ASIACCS) PDF

April 2017

Markov Modeling of Moving Target Defense Games

Hoda Maleki, Saeed Valizadeh,William Koch, Azer Bestavros, Marten van Dijk

ACM Workshop on Moving Target Defense PDF

October 2016

Experience

Founder/Organizer

Boston Drone Racing

Boston Drone Racing (BDR) is a first-person view (FPV) unmanned aerial vehicle (UAV) racing and hacking club. Born from academia, BDR fosters a learning environment and community to teach others how to fly and the knowledge and skills needed to get into the sport. Additionally BDR is actively applying theory and research to push the performance of the technologies used in the sport.

As founder, created website, logo and established communication and organization channels. Secured funding for racing track and supplies. Website

April 2017 - Present

Cyber Security Intern

MIT Lincoln Laboratory

Developed novel SDN attack called Persona Hijacking that breaks the bindings of all layers of the networking stack and fools the network infrastructure into believing that the attacker is the legitimate owner of the victim’s identifiers, which significantly increases persistence. Results have been published in USENIX Security Symposium.

January 2016 - June 2016

Software Engineer

Sikorsky Aircraft (contracted by Sila Solutions)

Lead software engineer on several software applications for the Sikorsky CH-53K Aircraft's Integrated Support System (ISS). Designed and implemented continuous integration system. Responsible for integration between third-party vendors.

June 2006 - January 2012

Chairman/Co-founder

CT Hackerspace

CT Hackerspace is Connecticut's oldest and largest hackerspace/makerspace. As a co-founder, established organization through the development of bylaws, identity, physical and web presence. As chairman, ran monthly board meetings to facilitate in the growth and direction of the hackerspace. Republican American Article - Website

August 2010 - August 2011

Teaching

Teaching Fellow

Boston University

Teaching fellow for CS-350 Fundamentals of Computing Systems. Designed lesson plans and taught discussion sections. Developed written and programming assignments.

Fall 2017, Spring 2019

Programming Instructor

iD Tech Camps - Princeton University

Created lesson plans for wide range of skill levels including object oriented fundamentals, polymorphism, exception handling and third-party library integration. Emphasized lessons on coding style and best practices not taught and enforced in academia. Advised students through projects ranging from web crawlers to video games.

June 2012-August 2012

Education

Boston University

Doctor of Philosophy
Computer Science - Intelligent Flight Control Systems

Thesis title: Flight Controller Synthesis via Deep Reinforcement Learning PDF

GPA: 3.8

September 2014 - September 2019

Stevens Institute of Technology

Masters of Science
Computer Engineering - Machine Learning

Thesis title: A Framework for Assisting Learners by Incorporating Knowledge to Aid in Predicting Nerve Guidance Conduit Performance PDF

GPA: 3.8

January 2012 - December 2013

University of Rhode Island

Bachelor of Science
Computer Engineering - Robotics

GPA: 3.2

September 2003 - May 2008