Alex Shepherd

About

I am a senior researcher at the Institute for Ethical AI at Oxford Brookes University and an MPA candidate at the Department of Science, Technology, Engineering and Public Policy at UCL.

Email: ashepherd [at] brookes [dot] ac [dot] uk

Research Interests

• Language-theoretic security
• Weird machines
• Return-oriented programming
• Adversarial ML

Writing

• Subverting Neural Networks via Adversarial Reprogramming [blog post]
• Attacking Machine Vision Models In Real Life [blog post]
• The Infinite Game of Disinformation [blog post]
• ‘It’s Complicated’: The Relationship Between Artificial Intelligence and the Fourth Estate [blog post]

Media

• 'It's very cheap to be a bad faith actor' -- why disinformation is an 'infinite game' [podcast interview]