1 citations · 1 across the 4 of their papers we have counts for
4 papers
Beyond Slow Signs in High-fidelity Model Extraction
Hanna Foerster, Robert Mullins, Ilia Shumailov +1
Deep neural networks, costly to train and rich in intellectual property value, are increasingly threatened by model extraction attacks that compromise their confidentiality. Previo…
Human-Producible Adversarial Examples
David Khachaturov, Yue Gao, Ilia Shumailov +3
Visual adversarial examples have so far been restricted to pixel-level image manipulations in the digital world, or have required sophisticated equipment such as 2D or 3D printers…
Dynamic Stashing Quantization for Efficient Transformer Training
Guo Yang, Daniel Lo, Robert Mullins +1
Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. Unfortunately, the immense amount of computations and m…
Efficient Adversarial Training With Data Pruning
Maximilian Kaufmann, Yiren Zhao, Ilia Shumailov +2
Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial exa…