Image Hijacks: Adversarial Images can Control Generative Models at Runtime
I've just finished my undergraduate degree in Computer Science at the University of Cambridge (where I ranked 1st / ~120 every year), and I'm currently a research assistant at ml@cl under Dr Ferenc Huszár .
My ambition is to develop powerful, yet safe and interpretable abstract reasoners, whose internal state and behaviour remain transparent to the end user .
To this end, I'm particularly interested in exploring how the mathematical toolkits we use to understand and structure programs ‒ such as formal methods , types and category theory ‒ can inspire new ways to both reverse-engineer existing neural networks, and build scalable neurosymbolic systems.
Image Hijacks: Adversarial Images can Control Generative Models at Runtime