Fred Hohman

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

2020

Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully-crafted perturbations on data inputs that can fool a model into making incorrect predictions. Despite significant research …

BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks

2024 · arXiv (Cornell University)

Programmers frequently engage with machine learning tutorials in computational notebooks and have been adopting code generation technologies based on large language models (LLMs). However, they encounter difficulties in understanding and working with code produced by …