A little robustness goes a long way: Leveraging robust features for targeted transfer attacks J Springer, M Mitchell, G Kenyon Advances in Neural Information Processing Systems 34, 9759-9773, 2021 | 33 | 2021 |
It's hard for neural networks to learn the game of life JM Springer, GT Kenyon 2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021 | 27 | 2021 |
Understanding catastrophic forgetting in language models via implicit inference S Kotha, JM Springer, A Raghunathan arXiv preprint arXiv:2309.10105, 2023 | 14 | 2023 |
Adversarial perturbations are not so weird: Entanglement of robust and non-robust features in neural network classifiers JM Springer, M Mitchell, GT Kenyon arXiv preprint arXiv:2102.05110, 2021 | 10 | 2021 |
Teaching with angr: A symbolic execution curriculum and {CTF} J Springer, W Feng 2018 USENIX Workshop on Advances in Security Education (ASE 18), 2018 | 10 | 2018 |
Classifiers based on deep sparse coding architectures are robust to deep learning transferable examples JM Springer, CS Strauss, AM Thresher, E Kim, GT Kenyon arXiv preprint arXiv:1811.07211, 2018 | 9 | 2018 |
STRATA: Simple, Gradient-Free Attacks for Models of Code JM Springer, BM Reinstadler, UM O'Reilly arXiv preprint arXiv:2009.13562, 2020 | 8* | 2020 |
If you’ve trained one you’ve trained them all: inter-architecture similarity increases with robustness HT Jones, JM Springer, GT Kenyon, JS Moore Uncertainty in Artificial Intelligence, 928-937, 2022 | 7 | 2022 |
Uncovering Universal Features: How Adversarial Training Improves Adversarial Transferability JM Springer, M Mitchell, GT Kenyon ICML 2021 Workshop on Adversarial Machine Learning, 2021 | 6 | 2021 |
Repetition Improves Language Model Embeddings JM Springer, S Kotha, D Fried, G Neubig, A Raghunathan arXiv preprint arXiv:2402.15449, 2024 | 3 | 2024 |
Sparse mp4 DA Wang, CMS Strauss, JM Springer, A Thresher, H Pritchard, ... 2020 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI …, 2020 | 2 | 2020 |
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning JM Springer, V Nagarajan, A Raghunathan The Twelfth International Conference on Learning Representations, 0 | | |