1

Towards certificated model robustness against weight perturbations

This work studies the sensitivity of neural networks to weight perturbations, firstly corresponding to a newly developed threat model that perturbs the neural network parameters. We propose an efficient approach to compute a certified robustness …

Towards query-efficient black-box adversary with zeroth-order natural gradient descent

Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-ofthe-art DNNs raises security concerns in many application domains requiring high reliability. Various adversarial attacks are proposed …

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method

Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations. Despite the …

Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability. We propose the fault sneaking attack on DNNs, where the …

HSIM-DNN: Hardware Simulator for Computation-, Storage- and Power-Efficient Deep Neural Networks

Deep learning that utilizes large-scale deep neural networks (DNNs) is effective in automatic high-level feature extraction but also computation and memory intensive. Constructing DNNs using blockcirculant matrices can simultaneously achieve hardware …

Structured Adversarial Attack: Towards General Implementation and Better Interpretability

When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks perturbing the …

Admm attack: an enhanced adversarial attack for deep neural networks with undetectable distortions

Many recent studies demonstrate that state-of-the-art Deep neural networks (DNNs) might be easily fooled by adversarial examples, generated by adding carefully crafted and visually imperceptible distortions onto original legal inputs through …

Defending DNN Adversarial Attacks with Pruning and Logits Augmentation

Deep neural networks (DNNs) have been shown to be powerful models and perform extremely well on many complicated artificial intelligent tasks. However, recent research found that these powerful models are vulnerable to adversarial attacks, i.e., …

Reinforced Adversarial Attacks on Deep Neural Networks Using ADMM

As deep learning penetrates into wide application domains, it is essential to evaluate the robustness of deep neural networks (DNNs) under adversarial attacks, especially for some security-critical applications. To better understand the security …

Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. This work …