Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Adversarial vulnerability for any classifier
Authors: Alhussein Fawzi, Hamza Fawzi, Omar Fawzi
NeurIPS 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conclude with numerical experimental results showing that our bounds provide informative baselines to the maximal achievable robustness on several datasets. We evaluate our bounds in several experimental setups (CIFAR-10 and SVHN), and show that they yield informative baselines to the maximal achievable robustness. |
| Researcher Affiliation | Collaboration | Alhussein Fawzi Deep Mind EMAIL Hamza Fawzi Department of Applied Mathematics & Theoretical Physics University of Cambridge EMAIL Omar Fawzi ENS de Lyon EMAIL |
| Pseudocode | No | The paper does not contain any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that open-source code for the described methodology is available. |
| Open Datasets | Yes | We now evaluate our bounds on the SVHN dataset [37] which contains color images of house numbers... We now consider the more complex CIFAR-10 dataset [39]. |
| Dataset Splits | No | The paper specifies training and test image counts for SVHN (73,257 training, 26,032 test) but does not explicitly mention a separate validation split or its size/percentage. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as GPU models or CPU specifications. |
| Software Dependencies | No | The paper mentions using a DCGAN model and neural network architectures, but it does not specify any software names with version numbers for reproducibility (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | We train a DCGAN [30] generative model on this dataset, with a latent vector dimension d = 100, and further consider several neural networks architectures for classification. |