T. P. Trzcinski

Zero Time Waste: Recycling Predictions in Early Exit Neural Networks

2021 · arXiv (Cornell University)

The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by attaching additional Internal Classifiers (ICs) to intermediate layers …

The Tunnel Effect: Building Data Representations in Deep Neural Networks

2023 · arXiv (Cornell University)

Deep neural networks are widely known for their remarkable effectiveness across various tasks, with the consensus that deeper networks implicitly learn more complex data representations. This paper shows that sufficiently deep networks trained for supervised …

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

2023 · arXiv (Cornell University)

Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costly to train, they become lucrative targets for model stealing attacks …