There have been many recent attempts to extend the successes of convolutional neural networks (CNNs) from 2-dimensional (2D) image classification to 3-dimensional (3D) video recognition by exploring 3D CNNs. Considering the emerging growth of mobile …
High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications. However, the constrained computation and storage resources on these devices still pose significant challenges for …
There have been many recent attempts to extend the successes of convolutional neural networks (CNNs) from 2-dimensional (2D) image classification to 3-dimensional (3D) video recognition by exploring 3D CNNs. Considering the emerging growth of mobile …
Mode connectivity provides novel geometric insights on analyzing loss landscapes and enables building high-accuracy pathways between well-trained neural networks. In this work, we propose to employ mode connectivity in loss landscapes to study the …
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 …
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 …
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 …
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 …
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 …
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 …