Search Results for author:
Found 5 papers, 4 papers with code
On the Robustness of Randomized Ensembles to Adversarial Perturbations
In this work, we first demystify RECs as we derive fundamental results regarding their theoretical limits, necessary and sufficient conditions for them to be useful, and more.
Adversarial Vulnerability of Randomized Ensembles
In this work we address this question both theoretically and empirically.
Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks
But these methods are unable to improve throughput (frames-per-second) on real-life hardware while simultaneously preserving robustness to adversarial perturbations.
Robustifying $\ell_\infty$ Adversarial Training to the Union of Perturbation Models
Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $\ell_\infty$ norm-bounded perturbations.
Energy-efficient Machine Learning in Silicon: A Communications-inspired Approach
This position paper advocates a communications-inspired approach to the design of machine learning systems on energy-constrained embedded `always-on' platforms.
