Publications

(2023). Privacy Side Channels in Machine Learning Systems. arXiv.

PDF Cite

(2023). Evading Black-box Classifiers Without Breaking Eggs. ICML 2023 Workshop on Frontiers in AdvML, Oral presentation.

PDF Cite Code Poster Slides Video

(2022). A Light Recipe to Train Robust Vision Transformers. IEEE SaTML 2023.

PDF Cite Code Poster Slides Video

(2022). Adversarially Robust Vision Transformers. EPFL.

PDF Cite

(2021). RobustBench: A standardized benchmark for adversarial robustness. NeurIPS 2021 Datasets and Benchmarks Track.

PDF Cite Code