Search Results for author:
Found 7 papers, 3 papers with code
Hindering Adversarial Attacks with Implicit Neural Representations
We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR-$10$ classifiers for perturbations up to $\epsilon = 8/255$ in $L_\infty$ norm and $\epsilon = 0. 5$ in $L_2$ norm.
Data Augmentation Can Improve Robustness
Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training.
Defending Against Image Corruptions Through Adversarial Augmentations
Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog.
Fixing Data Augmentation to Improve Adversarial Robustness
In particular, against $\ell_\infty$ norm-bounded perturbations of size $\epsilon = 8/255$, our model reaches 64. 20% robust accuracy without using any external data, beating most prior works that use external data.
Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecification
Many real-world physical control systems are required to satisfy constraints upon deployment.
Balancing Constraints and Rewards with Meta-Gradient D4PG
Deploying Reinforcement Learning (RL) agents to solve real-world applications often requires satisfying complex system constraints.
SCRAM: Spatially Coherent Randomized Attention Maps
The central idea of SCRAM is to employ PatchMatch, a randomized correspondence algorithm, to quickly pinpoint the most compatible key (argmax) for each query first, and then exploit that knowledge to design a sparse approximation to non-local mean operations.
