Search Results for author:
Found 6 papers, 3 papers with code
Accelerating Certified Robustness Training via Knowledge Transfer
Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems.
Ares: A System-Oriented Wargame Framework for Adversarial ML
Since the discovery of adversarial attacks against machine learning models nearly a decade ago, research on adversarial machine learning has rapidly evolved into an eternal war between defenders, who seek to increase the robustness of ML models against adversarial attacks, and adversaries, who seek to develop better attacks capable of weakening or defeating these defenses.
Transferring Adversarial Robustness Through Robust Representation Matching
On CIFAR-10, RRM trains a robust model $\sim 1. 8\times$ faster than the state-of-the-art.
Can Attention Masks Improve Adversarial Robustness?
Focusing on the observation that discrete pixelization in MNIST makes the background completely black and foreground completely white, we hypothesize that the important property for increasing robustness is the elimination of image background using attention masks before classifying an object.
Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders
Numerous techniques have been proposed to harden machine learning algorithms and mitigate the effect of adversarial attacks.
Robust Classification using Robust Feature Augmentation
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image.
