Publication

Found 3 results
Author Title Type [ Year(Desc)]
Filters: Author is Stephen Casper  [Clear All Filters]
2021
Casper, S. et al. Frivolous Units: Wider Networks Are Not Really That Wide. AAAI 2021 (2021). at <https://dblp.org/rec/conf/aaai/CasperBDGSVK21.html>PDF icon 1912.04783.pdf (6.69 MB)
2022
Casper, S., Nadeau, M. & Kreiman, G. One thing to fool them all: generating interpretable, universal, and physically-realizable adversarial features. arXiv (2022). doi:10.48550/arXiv.2110.03605PDF icon 2110.03605.pdf (6.7 MB)
Casper, S., Nadeau, M., Hadfield-Menell, D. & Kreiman, G. Robust Feature-Level Adversaries are Interpretability Tools. NeurIPS (2022). at <https://openreview.net/forum?id=lQ--doSB2o>PDF icon 8789_robust_feature_level_adversari.pdf (3.79 MB)