Pinned Repositories
blackbox-attacks-eccv
Code used in 'Exploring the Space of Black-box Attacks on Deep Neural Networks' (https://arxiv.org/abs/1712.09491)
C_D_M_mlsec
cleverhans
A library for benchmarking vulnerability to adversarial examples
data-defense-2
New defenses from data properties
ensemble-adv-training
Ensemble Adversarial Training on MNIST
log-loss-lower-bounds
ml_defense
mnist_challenge
A challenge to explore adversarial robustness of neural networks on MNIST.
nn_robust_attacks
Robust evasion attacks against neural network to find adversarial examples
quantqc
Finds high-girth self-dual LDPC codes using Hagiwara and Imai's method (2007)
arjunbhagoji's Repositories
arjunbhagoji/ml_defense
arjunbhagoji/log-loss-lower-bounds
arjunbhagoji/quantqc
Finds high-girth self-dual LDPC codes using Hagiwara and Imai's method (2007)
arjunbhagoji/cleverhans
A library for benchmarking vulnerability to adversarial examples
arjunbhagoji/mnist_challenge
A challenge to explore adversarial robustness of neural networks on MNIST.
arjunbhagoji/nn_robust_attacks
Robust evasion attacks against neural network to find adversarial examples
arjunbhagoji/blackbox-attacks-eccv
Code used in 'Exploring the Space of Black-box Attacks on Deep Neural Networks' (https://arxiv.org/abs/1712.09491)
arjunbhagoji/C_D_M_mlsec
arjunbhagoji/data-defense-2
New defenses from data properties
arjunbhagoji/ensemble-adv-training
Ensemble Adversarial Training on MNIST
arjunbhagoji/influence-release
arjunbhagoji/lucid
A collection of infrastructure and tools for research in neural network interpretability.
arjunbhagoji/network-data-sharing
arjunbhagoji/semantic-seg-attacks
DeepLab-ResNet rebuilt in TensorFlow
arjunbhagoji/ZOO-Attack-mine
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks