Search Results for author:
Found 4 papers, 1 papers with code
DAEs for Linear Inverse Problems: Improved Recovery with Provable Guarantees
Generative priors have been shown to provide improved results over sparsity priors in linear inverse problems.
Compressive Recovery Defense: A Defense Framework for $\ell_0, \ell_2$ and $\ell_\infty$ norm attacks.
We provide recovery guarantees for compressible signals that have been corrupted with noise and extend the framework introduced in \cite{bafna2018thwarting} to defend neural networks against $\ell_0$, $\ell_2$, and $\ell_{\infty}$-norm attacks.
Recovery Guarantees for Compressible Signals with Adversarial Noise
For $\ell_2$-norm bounded noise, we provide recovery guarantees for BP and for the case of $\ell_\infty$-norm bounded noise, we provide recovery guarantees for Dantzig Selector (DS).
Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning
Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network.
